Duplicate from lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled
Browse files- .gitattributes +36 -0
- README.md +158 -0
- chat_template.jinja +158 -0
- config.json +126 -0
- model-00001-of-00026.safetensors +3 -0
- model-00002-of-00026.safetensors +3 -0
- model-00003-of-00026.safetensors +3 -0
- model-00004-of-00026.safetensors +3 -0
- model-00005-of-00026.safetensors +3 -0
- model-00006-of-00026.safetensors +3 -0
- model-00007-of-00026.safetensors +3 -0
- model-00008-of-00026.safetensors +3 -0
- model-00009-of-00026.safetensors +3 -0
- model-00010-of-00026.safetensors +3 -0
- model-00011-of-00026.safetensors +3 -0
- model-00012-of-00026.safetensors +3 -0
- model-00013-of-00026.safetensors +3 -0
- model-00014-of-00026.safetensors +3 -0
- model-00015-of-00026.safetensors +3 -0
- model-00016-of-00026.safetensors +3 -0
- model-00017-of-00026.safetensors +3 -0
- model-00018-of-00026.safetensors +3 -0
- model-00019-of-00026.safetensors +3 -0
- model-00020-of-00026.safetensors +3 -0
- model-00021-of-00026.safetensors +3 -0
- model-00022-of-00026.safetensors +3 -0
- model-00023-of-00026.safetensors +3 -0
- model-00024-of-00026.safetensors +3 -0
- model-00025-of-00026.safetensors +3 -0
- model-00026-of-00026.safetensors +3 -0
- model.safetensors.index.json +1052 -0
- processor_config.json +63 -0
- tokenizer.json +3 -0
- tokenizer_config.json +34 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: transformers
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
base_model: Qwen/Qwen3.6-35B-A3B
|
| 8 |
+
datasets:
|
| 9 |
+
- lordx64/reasoning-distill-opus-4-7-max-sft
|
| 10 |
+
tags:
|
| 11 |
+
- text-generation
|
| 12 |
+
- reasoning
|
| 13 |
+
- distillation
|
| 14 |
+
- chain-of-thought
|
| 15 |
+
- qwen
|
| 16 |
+
- qwen3.6
|
| 17 |
+
- mixture-of-experts
|
| 18 |
+
- moe
|
| 19 |
+
- lora
|
| 20 |
+
- unsloth
|
| 21 |
+
model-index:
|
| 22 |
+
- name: Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled
|
| 23 |
+
results: []
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
# Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled
|
| 27 |
+
|
| 28 |
+
A reasoning-distilled variant of **Qwen3.6-35B-A3B** taught to imitate the chain-of-thought style of **Claude Opus 4.7**, the frontier reasoning model from Anthropic. The goal: port Claude-grade reasoning behavior into a permissively-licensed Mixture-of-Experts model that an individual can actually run.
|
| 29 |
+
|
| 30 |
+
## Why this model
|
| 31 |
+
|
| 32 |
+
- **Claude-style reasoning, open weights.** Claude Opus 4.7 is one of the strongest reasoning models available, but only via a proprietary API. This model has been fine-tuned on ~8k high-quality reasoning traces produced by Opus 4.7, teaching the base to *think* before answering — with explicit `<think>…</think>` blocks — in Claude's structure and cadence.
|
| 33 |
+
- **Sparse activation, dense knowledge.** The base is a 35B-parameter MoE with **256 experts, 8 routed + 1 shared**, of which only about **3B parameters are active** per token. You get the capacity of a 35B model at the inference cost of a small dense model. Full-quality bf16 inference runs on a single 80GB A100 or H100.
|
| 34 |
+
- **Long thinking supported.** 64k token context. The model routinely emits 5–30k tokens of `<think>` reasoning on hard problems before giving the final answer — which is the whole point of reasoning models, and why this one was specifically trained end-to-end with an upstream teacher that also reasons explicitly.
|
| 35 |
+
- **Clean base to build on.** LoRA adapter is also published separately (`…-adapter`), so you can apply the distillation to other checkpoints of the same base, or stack further fine-tunes.
|
| 36 |
+
|
| 37 |
+
## Intended use
|
| 38 |
+
|
| 39 |
+
Built for hard reasoning: graduate-level STEM, competition math (AIME / MATH), code reasoning with explicit walk-through, multi-step logic puzzles, and agentic planning where explicit `<think>` helps correctness.
|
| 40 |
+
|
| 41 |
+
For short-turn conversational latency-sensitive workloads the thinking budget can be large; cap `max_new_tokens` or post-process to strip `<think>…</think>` blocks if you only want final answers in production.
|
| 42 |
+
|
| 43 |
+
## How to use
|
| 44 |
+
|
| 45 |
+
```python
|
| 46 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 47 |
+
import torch
|
| 48 |
+
|
| 49 |
+
repo = "lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled"
|
| 50 |
+
tok = AutoTokenizer.from_pretrained(repo)
|
| 51 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 52 |
+
repo, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True,
|
| 53 |
+
)
|
| 54 |
+
|
| 55 |
+
messages = [{"role": "user", "content": "How many positive integers less than 1000 have digits that sum to 20?"}]
|
| 56 |
+
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
| 57 |
+
out = model.generate(inputs, max_new_tokens=32768, do_sample=False)
|
| 58 |
+
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
|
| 59 |
+
```
|
| 60 |
+
|
| 61 |
+
Recommended backend: **vLLM** for serving — the MoE routing + KV cache benefit significantly from continuous batching.
|
| 62 |
+
```
|
| 63 |
+
vllm serve lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled \
|
| 64 |
+
--dtype bfloat16 --max-model-len 65536 --gpu-memory-utilization 0.9
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
### GGUF (LM Studio / llama.cpp)
|
| 68 |
+
|
| 69 |
+
Quantized GGUF weights are available for `llama.cpp` and LM Studio:
|
| 70 |
+
|
| 71 |
+
- [**IQ4_XS** (18.9 GB)](https://huggingface.co/lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-IQ4_XS-GGUF) — fits in ~24 GB RAM/VRAM, default pick for LM Studio
|
| 72 |
+
|
| 73 |
+
Search `lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled` inside LM Studio's model browser once HF has indexed the GGUF repo (usually within an hour of publication). More quant levels (`Q4_K_M`, `Q5_K_M`, `Q8_0`) can be added on request.
|
| 74 |
+
|
| 75 |
+
## Training
|
| 76 |
+
|
| 77 |
+
| | |
|
| 78 |
+
|---|---|
|
| 79 |
+
| Base model | `Qwen/Qwen3.6-35B-A3B` (loaded via `unsloth/Qwen3.6-35B-A3B` for faster finetuning) |
|
| 80 |
+
| Teacher | Claude Opus 4.7 (Anthropic) |
|
| 81 |
+
| Training dataset | [`lordx64/reasoning-distill-opus-4-7-max-sft`](https://huggingface.co/datasets/lordx64/reasoning-distill-opus-4-7-max-sft) — reasoning traces from Claude Opus 4.7 reformatted into SFT conversations |
|
| 82 |
+
| Source dataset | [`lordx64/reasoning-distill-claude-opus-4-7-max`](https://huggingface.co/datasets/lordx64/reasoning-distill-claude-opus-4-7-max) — raw teacher traces (pre-SFT formatting) |
|
| 83 |
+
| Dataset size | ~7,800 full conversations, assistant side trained including `<think>…</think>` |
|
| 84 |
+
| Method | SFT with Unsloth + TRL `SFTTrainer` + `train_on_responses_only` (loss only on assistant tokens) |
|
| 85 |
+
| LoRA config | `r=16, alpha=16, dropout=0.0, targets=["q_proj","k_proj","v_proj","o_proj"]` (attention-only) |
|
| 86 |
+
| Hyperparameters | `lr=2e-5`, cosine schedule, `warmup_ratio=0.03`, `weight_decay=0.01`, optimizer `adamw_8bit` |
|
| 87 |
+
| Batch | `per_device=1, grad_accum=16, effective=16`, 2 epochs = 978 steps |
|
| 88 |
+
| Sequence | 4096 tokens during training (64k usable at inference — base supports it natively) |
|
| 89 |
+
| Precision | bf16 on 1× H200 141GB (HF Inference Endpoint, custom container) |
|
| 90 |
+
| Trainable | 3.44M params out of 35.1B (0.01%) |
|
| 91 |
+
|
| 92 |
+
### Why attention-only LoRA on a MoE
|
| 93 |
+
|
| 94 |
+
The initial plan was full LoRA including the MoE expert FFNs (`gate_proj/up_proj/down_proj`). In the course of this project I filed and upstreamed a shape-mismatch fix to unsloth-zoo's MoE+LoRA grouped-mm path — [unslothai/unsloth-zoo#601](https://github.com/unslothai/unsloth-zoo/pull/601) — without which the expert-LoRA forward crashes on Qwen3.6's 256-expert layout. Even with that fix, single-GPU memory made expert-LoRA impractical for this run. Attention-only captures most of the signal on *style* distillation anyway (the point of this model) while leaving the expert FFNs' learned knowledge intact — a v2 training run with expert LoRA on multi-GPU is a natural next step if the style-only signal isn't enough.
|
| 95 |
+
|
| 96 |
+
## Evaluation
|
| 97 |
+
|
| 98 |
+
Evaluated via `lm-evaluation-harness` (v0.4.9) with vLLM backend at 64k context, bf16. Custom eval path strips `<think>…</think>` from generations before the filter pipeline, uses per-task conventional fewshot counts, and runs with `fewshot_as_multiturn=True` so few-shot examples are proper chat turns rather than concatenated prompt text. Raw results JSON is public: [lordx64/qwen3-6-distill-evals](https://huggingface.co/datasets/lordx64/qwen3-6-distill-evals).
|
| 99 |
+
|
| 100 |
+
| Benchmark | Setup | Score |
|
| 101 |
+
|---|---|---|
|
| 102 |
+
| **GSM8K CoT** | 8-shot multiturn, limit 300 | **84.3%** (flexible-extract) / 76.7% (strict-match) |
|
| 103 |
+
| **MMLU-Pro** | 5-shot multiturn, limit 500 | **74.9%** |
|
| 104 |
+
| AIME 2024 | 0-shot, full (30) | _extraction fix in progress — model generates answers but not in a format the AIME extractor recognizes (`\boxed{}` vs plain prose)_ |
|
| 105 |
+
| AIME 2025 | 0-shot, full (30) | _same — pending_ |
|
| 106 |
+
| GPQA Diamond | 0-shot CoT, full (198) | _same — pending_ |
|
| 107 |
+
| MATH-500 | 0-shot, limit 100 | _rerun pending (missing `sympy` / `math_verify` dep in the first run)_ |
|
| 108 |
+
|
| 109 |
+
### MMLU-Pro subject breakdown
|
| 110 |
+
|
| 111 |
+
Standard reasoning-model profile: strong on STEM, weaker on law/engineering. All subjects evaluated at limit 500, 5-shot multiturn.
|
| 112 |
+
|
| 113 |
+
| Subject | Acc | Subject | Acc |
|
| 114 |
+
|---|---:|---|---:|
|
| 115 |
+
| Biology | 86.0% | Chemistry | 78.8% |
|
| 116 |
+
| Psychology | 83.4% | Health | 73.8% |
|
| 117 |
+
| Math | 83.6% | Business | 74.4% |
|
| 118 |
+
| Economics | 83.0% | Other | 72.6% |
|
| 119 |
+
| Physics | 81.0% | Philosophy | 71.3% |
|
| 120 |
+
| Computer Science | 79.0% | History | 70.9% |
|
| 121 |
+
| | | **Engineering** | **54.8%** |
|
| 122 |
+
| | | **Law** | **55.6%** |
|
| 123 |
+
|
| 124 |
+
Full per-task JSON with stderr, filter configs, and timings lives in the [evals dataset](https://huggingface.co/datasets/lordx64/qwen3-6-distill-evals/tree/main/reasoning/lordx64__Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled). The remaining tasks will be added to this table after a diagnostic rerun identifies why AIME/GPQA extraction is returning no-match on generated outputs.
|
| 125 |
+
|
| 126 |
+
## Limitations
|
| 127 |
+
|
| 128 |
+
- **Reasoning ≠ knowledge.** Distillation transfers *how to reason*, not new facts. Anything the base Qwen3.6-35B-A3B doesn't already know, this model still doesn't know.
|
| 129 |
+
- **Attention-only LoRA.** Expert FFNs are untouched from the base — domains where Claude and Qwen3.6 diverge in factual priors may see uneven improvement.
|
| 130 |
+
- **Long generations.** The model will genuinely use tens of thousands of tokens on hard problems. Budget your `max_new_tokens` accordingly, and provide `max_model_len ≥ 32k` at inference.
|
| 131 |
+
- **Distillation provenance.** Training data was generated with Anthropic's Claude Opus 4.7 via API. Downstream users should confirm compliance with Anthropic's [usage policies](https://www.anthropic.com/legal/usage-policy) for their specific use case.
|
| 132 |
+
|
| 133 |
+
## Citation
|
| 134 |
+
|
| 135 |
+
If you use this model, please cite the base and the distillation:
|
| 136 |
+
|
| 137 |
+
```bibtex
|
| 138 |
+
@misc{qwen36_a3b_2026,
|
| 139 |
+
title = {Qwen3.6-35B-A3B},
|
| 140 |
+
author = {Qwen Team},
|
| 141 |
+
year = {2026},
|
| 142 |
+
howpublished = {\url{https://huggingface.co/Qwen/Qwen3.6-35B-A3B}},
|
| 143 |
+
}
|
| 144 |
+
|
| 145 |
+
@misc{lordx64_qwen36_distill_2026,
|
| 146 |
+
title = {Qwen3.6-35B-A3B distilled from Claude Opus 4.7 reasoning},
|
| 147 |
+
author = {lordx64},
|
| 148 |
+
year = {2026},
|
| 149 |
+
howpublished = {\url{https://huggingface.co/lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled}},
|
| 150 |
+
}
|
| 151 |
+
```
|
| 152 |
+
|
| 153 |
+
## Acknowledgements
|
| 154 |
+
|
| 155 |
+
- **Unsloth** — 2× faster training of large MoE LoRA; the bug we hit and fixed was in their `unsloth-zoo` patches (credit for rapid review of PR #601).
|
| 156 |
+
- **Anthropic** — for the teacher model.
|
| 157 |
+
- **Qwen team** — for releasing Qwen3.6 with a permissive Apache-2.0 license, enabling work like this.
|
| 158 |
+
- **lm-evaluation-harness (EleutherAI)** — evaluation methodology.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- set num_sys = 0 %}
|
| 46 |
+
{%- set merged_system = '' %}
|
| 47 |
+
{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
|
| 48 |
+
{%- set first = render_content(messages[0].content, false, true)|trim %}
|
| 49 |
+
{%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
|
| 50 |
+
{%- set second = render_content(messages[1].content, false, true)|trim %}
|
| 51 |
+
{%- set merged_system = first + '\n' + second %}
|
| 52 |
+
{%- set num_sys = 2 %}
|
| 53 |
+
{%- else %}
|
| 54 |
+
{%- set merged_system = first %}
|
| 55 |
+
{%- set num_sys = 1 %}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 59 |
+
{{- '<|im_start|>system\n' }}
|
| 60 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 61 |
+
{%- for tool in tools %}
|
| 62 |
+
{{- "\n" }}
|
| 63 |
+
{{- tool | tojson }}
|
| 64 |
+
{%- endfor %}
|
| 65 |
+
{{- "\n</tools>" }}
|
| 66 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 67 |
+
{%- if merged_system %}
|
| 68 |
+
{{- '\n\n' + merged_system }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{{- '<|im_end|>\n' }}
|
| 71 |
+
{%- else %}
|
| 72 |
+
{%- if merged_system %}
|
| 73 |
+
{{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 77 |
+
{%- for message in messages[::-1] %}
|
| 78 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 79 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 80 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 81 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 82 |
+
{%- set ns.multi_step_tool = false %}
|
| 83 |
+
{%- set ns.last_query_index = index %}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{%- endfor %}
|
| 87 |
+
{%- for message in messages %}
|
| 88 |
+
{%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
|
| 89 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 90 |
+
{%- if message.role == "user" %}
|
| 91 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 92 |
+
{%- elif message.role == "assistant" %}
|
| 93 |
+
{%- set reasoning_content = '' %}
|
| 94 |
+
{%- if message.reasoning_content is string %}
|
| 95 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 96 |
+
{%- else %}
|
| 97 |
+
{%- if '</think>' in content %}
|
| 98 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 99 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 100 |
+
{%- endif %}
|
| 101 |
+
{%- endif %}
|
| 102 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 103 |
+
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
|
| 104 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 105 |
+
{%- else %}
|
| 106 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 107 |
+
{%- endif %}
|
| 108 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 109 |
+
{%- for tool_call in message.tool_calls %}
|
| 110 |
+
{%- if tool_call.function is defined %}
|
| 111 |
+
{%- set tool_call = tool_call.function %}
|
| 112 |
+
{%- endif %}
|
| 113 |
+
{%- if loop.first %}
|
| 114 |
+
{%- if content|trim %}
|
| 115 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- else %}
|
| 120 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 121 |
+
{%- endif %}
|
| 122 |
+
{%- if tool_call.arguments is mapping %}
|
| 123 |
+
{%- for args_name in tool_call.arguments %}
|
| 124 |
+
{%- set args_value = tool_call.arguments[args_name] %}
|
| 125 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 126 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 127 |
+
{{- args_value }}
|
| 128 |
+
{{- '\n</parameter>\n' }}
|
| 129 |
+
{%- endfor %}
|
| 130 |
+
{%- endif %}
|
| 131 |
+
{{- '</function>\n</tool_call>' }}
|
| 132 |
+
{%- endfor %}
|
| 133 |
+
{%- endif %}
|
| 134 |
+
{{- '<|im_end|>\n' }}
|
| 135 |
+
{%- elif message.role == "tool" %}
|
| 136 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 137 |
+
{{- '<|im_start|>user' }}
|
| 138 |
+
{%- endif %}
|
| 139 |
+
{{- '\n<tool_response>\n' }}
|
| 140 |
+
{{- content }}
|
| 141 |
+
{{- '\n</tool_response>' }}
|
| 142 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 143 |
+
{{- '<|im_end|>\n' }}
|
| 144 |
+
{%- elif loop.last %}
|
| 145 |
+
{{- '<|im_end|>\n' }}
|
| 146 |
+
{%- endif %}
|
| 147 |
+
{%- endif %}
|
| 148 |
+
{%- endif %}
|
| 149 |
+
{%- endfor %}
|
| 150 |
+
{%- if add_generation_prompt %}
|
| 151 |
+
{{- '<|im_start|>assistant\n' }}
|
| 152 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 153 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 154 |
+
{%- else %}
|
| 155 |
+
{{- '<think>\n' }}
|
| 156 |
+
{%- endif %}
|
| 157 |
+
{%- endif %}
|
| 158 |
+
{#- Unsloth fixes - developer role, tool calling #}
|
config.json
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5MoeForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"torch_dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 248046,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_name": "unsloth/Qwen3.6-35B-A3B",
|
| 10 |
+
"model_type": "qwen3_5_moe",
|
| 11 |
+
"pad_token_id": 248055,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"attention_bias": false,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"attn_output_gate": true,
|
| 16 |
+
"bos_token_id": 248044,
|
| 17 |
+
"torch_dtype": "bfloat16",
|
| 18 |
+
"eos_token_id": 248044,
|
| 19 |
+
"full_attention_interval": 4,
|
| 20 |
+
"head_dim": 256,
|
| 21 |
+
"hidden_act": "silu",
|
| 22 |
+
"hidden_size": 2048,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"full_attention"
|
| 65 |
+
],
|
| 66 |
+
"linear_conv_kernel_dim": 4,
|
| 67 |
+
"linear_key_head_dim": 128,
|
| 68 |
+
"linear_num_key_heads": 16,
|
| 69 |
+
"linear_num_value_heads": 32,
|
| 70 |
+
"linear_value_head_dim": 128,
|
| 71 |
+
"mamba_ssm_dtype": "float32",
|
| 72 |
+
"max_position_embeddings": 262144,
|
| 73 |
+
"model_type": "qwen3_5_moe_text",
|
| 74 |
+
"moe_intermediate_size": 512,
|
| 75 |
+
"mtp_num_hidden_layers": 1,
|
| 76 |
+
"mtp_use_dedicated_embeddings": false,
|
| 77 |
+
"num_attention_heads": 16,
|
| 78 |
+
"num_experts": 256,
|
| 79 |
+
"num_experts_per_tok": 8,
|
| 80 |
+
"num_hidden_layers": 40,
|
| 81 |
+
"num_key_value_heads": 2,
|
| 82 |
+
"output_router_logits": false,
|
| 83 |
+
"pad_token_id": null,
|
| 84 |
+
"partial_rotary_factor": 0.25,
|
| 85 |
+
"rms_norm_eps": 1e-06,
|
| 86 |
+
"rope_parameters": {
|
| 87 |
+
"mrope_interleaved": true,
|
| 88 |
+
"mrope_section": [
|
| 89 |
+
11,
|
| 90 |
+
11,
|
| 91 |
+
10
|
| 92 |
+
],
|
| 93 |
+
"partial_rotary_factor": 0.25,
|
| 94 |
+
"rope_theta": 10000000,
|
| 95 |
+
"rope_type": "default"
|
| 96 |
+
},
|
| 97 |
+
"router_aux_loss_coef": 0.001,
|
| 98 |
+
"shared_expert_intermediate_size": 512,
|
| 99 |
+
"tie_word_embeddings": false,
|
| 100 |
+
"use_cache": true,
|
| 101 |
+
"vocab_size": 248320
|
| 102 |
+
},
|
| 103 |
+
"tie_word_embeddings": false,
|
| 104 |
+
"unsloth_version": "2026.4.1",
|
| 105 |
+
"use_cache": false,
|
| 106 |
+
"video_token_id": 248057,
|
| 107 |
+
"vision_config": {
|
| 108 |
+
"deepstack_visual_indexes": [],
|
| 109 |
+
"depth": 27,
|
| 110 |
+
"torch_dtype": "bfloat16",
|
| 111 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 112 |
+
"hidden_size": 1152,
|
| 113 |
+
"in_channels": 3,
|
| 114 |
+
"initializer_range": 0.02,
|
| 115 |
+
"intermediate_size": 4304,
|
| 116 |
+
"model_type": "qwen3_5_moe",
|
| 117 |
+
"num_heads": 16,
|
| 118 |
+
"num_position_embeddings": 2304,
|
| 119 |
+
"out_hidden_size": 2048,
|
| 120 |
+
"patch_size": 16,
|
| 121 |
+
"spatial_merge_size": 2,
|
| 122 |
+
"temporal_patch_size": 2
|
| 123 |
+
},
|
| 124 |
+
"vision_end_token_id": 248054,
|
| 125 |
+
"vision_start_token_id": 248053
|
| 126 |
+
}
|
model-00001-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adee7bcb930aed22e0677e58d4873b48dadb1ed8001cb5c6a0487286eadb3478
|
| 3 |
+
size 3996199712
|
model-00002-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88f2dfd2b9e73e4b70be533dbf61bcfa3c9a0003758900fcbc9d9b96f5751d4b
|
| 3 |
+
size 1284907696
|
model-00003-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bcbe6420a532c2d2a30657b4ff3f0f4c6d40843aaebfbd50d68be3818e11294
|
| 3 |
+
size 3357898360
|
model-00004-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12d7db38689ba3c8af74b23ef8523eca41e0cd95db870583d0663a3ee8a6bd60
|
| 3 |
+
size 3370808712
|
model-00005-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4fcf07b8954e56eda92cf1103d7ef5727484bdfc323f5eef8bf5763b0609db1
|
| 3 |
+
size 3357898360
|
model-00006-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9080d718e9c5f9e337443225aa417d4c24d00ae7995d76ee3f1cc296b557d15
|
| 3 |
+
size 3959424904
|
model-00007-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8c05e23131b1dd45a455ec38cfac7db14667358268623c3938d00cf3e959a68
|
| 3 |
+
size 1096788232
|
model-00008-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:062546a6aac87eed6d5e18438845ae711d9178db0d6eb27929249a7d9104b480
|
| 3 |
+
size 3946842008
|
model-00009-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a31a954bb72d1c714e751bf0aabf2ff533f5a509693ebf7dd22ad6e90be46f67
|
| 3 |
+
size 1096460848
|
model-00010-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02b560690e2c05c1e07ec52902aabd0cd64480a85e29cbc717abde29821fcc92
|
| 3 |
+
size 3946841992
|
model-00011-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7180392817fe3ecb3a27a1da43b7ff22c1a94806bac49975f9f122c3126df675
|
| 3 |
+
size 1096460752
|
model-00012-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b47c5a65265b8b1b1f4d550a11587d67f66e39c98f7798e56c502c3ef30a67f
|
| 3 |
+
size 3409971080
|
model-00013-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33a20fb20a21379bf43c84a43105f9c0cc35bd50d740b1c302dcbe4b700f5425
|
| 3 |
+
size 1633331664
|
model-00014-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be823e33c5cb6120ad3769d081f34a2449dc2358041fca7c29d636c1ba19130d
|
| 3 |
+
size 3422553872
|
model-00015-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a89d547c6f9d0b535ee5ea2f2478f163089539f3f0dd330cb23d278a19d76123
|
| 3 |
+
size 1633659224
|
model-00016-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f71c93f4987f42636aebe49df96fe307ab3834fbe8ebf39a4ec5e4533fc9ea4
|
| 3 |
+
size 3946842136
|
model-00017-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e356e3943cf3852b76bb8992e674f3256013e27d54b78e8250514151cdc29637
|
| 3 |
+
size 1096460608
|
model-00018-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b45f0474bee313ce40f36cd986c026bf00ec5f521d84cbd03b3a4599b9b5e0d0
|
| 3 |
+
size 3946841992
|
model-00019-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:708644ad34f1de727bf484f396944d8ec628645d52c183e9a992e65671685e21
|
| 3 |
+
size 1096460808
|
model-00020-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef3969e9e20e86e8e10e963dc1ace1a6cdcbef3d31a2750d53857c9163a49b5e
|
| 3 |
+
size 3409971072
|
model-00021-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ada4ae48f3d48fe01b4c53f2f82bce25e798a9631fd33959c881156fef2ccbce
|
| 3 |
+
size 1633331744
|
model-00022-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:def207fb42d7db31efb512755557763c23233c6e4d4c433027cb5102a7bce2f7
|
| 3 |
+
size 3370808752
|
model-00023-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fa5fba3bcd66378c5e8bebd0ba1f13aec4a11137aedd0e09903e399709d0741
|
| 3 |
+
size 3357898392
|
model-00024-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:391acd27420cdce5935ff18152423c70620d19dac3c39a5ef1a81d369f82d737
|
| 3 |
+
size 3370808752
|
model-00025-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:778e7f76602f05042b69ba7f3ec91f1fdffef390540b16074041c258fb81d154
|
| 3 |
+
size 3832888256
|
model-00026-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:690fc9b473621944ebb86cba5808f7c835206a50ed581b6d5175a936d038c51d
|
| 3 |
+
size 2231416848
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1052 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 71903645408.0
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00026-of-00026.safetensors",
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00026.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00026.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00026.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00026.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00002-of-00026.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00026.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00026.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00026.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00026.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00002-of-00026.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00026.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.experts.down_proj": "model-00002-of-00026.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00026.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.gate.weight": "model-00002-of-00026.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00002-of-00026.safetensors",
|
| 22 |
+
"model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00002-of-00026.safetensors",
|
| 23 |
+
"model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00002-of-00026.safetensors",
|
| 24 |
+
"model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00002-of-00026.safetensors",
|
| 25 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00026.safetensors",
|
| 26 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00026.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00026.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00026.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00026.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00026.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00026.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00026.safetensors",
|
| 33 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00026.safetensors",
|
| 34 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00026.safetensors",
|
| 35 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00026.safetensors",
|
| 36 |
+
"model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00026.safetensors",
|
| 37 |
+
"model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00026.safetensors",
|
| 38 |
+
"model.language_model.layers.1.mlp.gate.weight": "model-00002-of-00026.safetensors",
|
| 39 |
+
"model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00002-of-00026.safetensors",
|
| 40 |
+
"model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00002-of-00026.safetensors",
|
| 41 |
+
"model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00002-of-00026.safetensors",
|
| 42 |
+
"model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00002-of-00026.safetensors",
|
| 43 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00026.safetensors",
|
| 44 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00007-of-00026.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00007-of-00026.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
|
| 47 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
|
| 48 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
|
| 49 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
|
| 50 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
|
| 51 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
|
| 52 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
|
| 53 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
|
| 54 |
+
"model.language_model.layers.10.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
|
| 55 |
+
"model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00007-of-00026.safetensors",
|
| 56 |
+
"model.language_model.layers.10.mlp.gate.weight": "model-00007-of-00026.safetensors",
|
| 57 |
+
"model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
|
| 58 |
+
"model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
|
| 59 |
+
"model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
|
| 60 |
+
"model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
|
| 61 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
|
| 62 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00009-of-00026.safetensors",
|
| 63 |
+
"model.language_model.layers.11.mlp.experts.down_proj": "model-00009-of-00026.safetensors",
|
| 64 |
+
"model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
|
| 65 |
+
"model.language_model.layers.11.mlp.gate.weight": "model-00009-of-00026.safetensors",
|
| 66 |
+
"model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
|
| 67 |
+
"model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
|
| 68 |
+
"model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
|
| 69 |
+
"model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
|
| 70 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
|
| 71 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00009-of-00026.safetensors",
|
| 72 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00008-of-00026.safetensors",
|
| 73 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00008-of-00026.safetensors",
|
| 74 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00009-of-00026.safetensors",
|
| 75 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00008-of-00026.safetensors",
|
| 76 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00008-of-00026.safetensors",
|
| 77 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00009-of-00026.safetensors",
|
| 78 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00009-of-00026.safetensors",
|
| 79 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00009-of-00026.safetensors",
|
| 80 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00009-of-00026.safetensors",
|
| 81 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00009-of-00026.safetensors",
|
| 82 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00009-of-00026.safetensors",
|
| 83 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00008-of-00026.safetensors",
|
| 84 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00008-of-00026.safetensors",
|
| 85 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00009-of-00026.safetensors",
|
| 86 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00008-of-00026.safetensors",
|
| 87 |
+
"model.language_model.layers.12.mlp.experts.down_proj": "model-00009-of-00026.safetensors",
|
| 88 |
+
"model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
|
| 89 |
+
"model.language_model.layers.12.mlp.gate.weight": "model-00009-of-00026.safetensors",
|
| 90 |
+
"model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
|
| 91 |
+
"model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
|
| 92 |
+
"model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
|
| 93 |
+
"model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
|
| 94 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
|
| 95 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00009-of-00026.safetensors",
|
| 96 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00009-of-00026.safetensors",
|
| 97 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00009-of-00026.safetensors",
|
| 98 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00009-of-00026.safetensors",
|
| 99 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00009-of-00026.safetensors",
|
| 100 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00009-of-00026.safetensors",
|
| 101 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00008-of-00026.safetensors",
|
| 102 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00008-of-00026.safetensors",
|
| 103 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00009-of-00026.safetensors",
|
| 104 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00008-of-00026.safetensors",
|
| 105 |
+
"model.language_model.layers.13.mlp.experts.down_proj": "model-00008-of-00026.safetensors",
|
| 106 |
+
"model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
|
| 107 |
+
"model.language_model.layers.13.mlp.gate.weight": "model-00009-of-00026.safetensors",
|
| 108 |
+
"model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
|
| 109 |
+
"model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
|
| 110 |
+
"model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
|
| 111 |
+
"model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
|
| 112 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
|
| 113 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00011-of-00026.safetensors",
|
| 114 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00011-of-00026.safetensors",
|
| 115 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00011-of-00026.safetensors",
|
| 116 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00011-of-00026.safetensors",
|
| 117 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00011-of-00026.safetensors",
|
| 118 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00011-of-00026.safetensors",
|
| 119 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00010-of-00026.safetensors",
|
| 120 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00010-of-00026.safetensors",
|
| 121 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00011-of-00026.safetensors",
|
| 122 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00010-of-00026.safetensors",
|
| 123 |
+
"model.language_model.layers.14.mlp.experts.down_proj": "model-00010-of-00026.safetensors",
|
| 124 |
+
"model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
|
| 125 |
+
"model.language_model.layers.14.mlp.gate.weight": "model-00011-of-00026.safetensors",
|
| 126 |
+
"model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
|
| 127 |
+
"model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
|
| 128 |
+
"model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
|
| 129 |
+
"model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
|
| 130 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
|
| 131 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00011-of-00026.safetensors",
|
| 132 |
+
"model.language_model.layers.15.mlp.experts.down_proj": "model-00011-of-00026.safetensors",
|
| 133 |
+
"model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
|
| 134 |
+
"model.language_model.layers.15.mlp.gate.weight": "model-00011-of-00026.safetensors",
|
| 135 |
+
"model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
|
| 136 |
+
"model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
|
| 137 |
+
"model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
|
| 138 |
+
"model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
|
| 139 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
|
| 140 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00011-of-00026.safetensors",
|
| 141 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00010-of-00026.safetensors",
|
| 142 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00010-of-00026.safetensors",
|
| 143 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00011-of-00026.safetensors",
|
| 144 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00010-of-00026.safetensors",
|
| 145 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00010-of-00026.safetensors",
|
| 146 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00011-of-00026.safetensors",
|
| 147 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00011-of-00026.safetensors",
|
| 148 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00011-of-00026.safetensors",
|
| 149 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00011-of-00026.safetensors",
|
| 150 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00011-of-00026.safetensors",
|
| 151 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00011-of-00026.safetensors",
|
| 152 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00010-of-00026.safetensors",
|
| 153 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00010-of-00026.safetensors",
|
| 154 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00011-of-00026.safetensors",
|
| 155 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00010-of-00026.safetensors",
|
| 156 |
+
"model.language_model.layers.16.mlp.experts.down_proj": "model-00011-of-00026.safetensors",
|
| 157 |
+
"model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
|
| 158 |
+
"model.language_model.layers.16.mlp.gate.weight": "model-00011-of-00026.safetensors",
|
| 159 |
+
"model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
|
| 160 |
+
"model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
|
| 161 |
+
"model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
|
| 162 |
+
"model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
|
| 163 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
|
| 164 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00013-of-00026.safetensors",
|
| 165 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00013-of-00026.safetensors",
|
| 166 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00013-of-00026.safetensors",
|
| 167 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00013-of-00026.safetensors",
|
| 168 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00013-of-00026.safetensors",
|
| 169 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00013-of-00026.safetensors",
|
| 170 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00012-of-00026.safetensors",
|
| 171 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00012-of-00026.safetensors",
|
| 172 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00013-of-00026.safetensors",
|
| 173 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00012-of-00026.safetensors",
|
| 174 |
+
"model.language_model.layers.17.mlp.experts.down_proj": "model-00012-of-00026.safetensors",
|
| 175 |
+
"model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00012-of-00026.safetensors",
|
| 176 |
+
"model.language_model.layers.17.mlp.gate.weight": "model-00013-of-00026.safetensors",
|
| 177 |
+
"model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
|
| 178 |
+
"model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
|
| 179 |
+
"model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
|
| 180 |
+
"model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
|
| 181 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
|
| 182 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00013-of-00026.safetensors",
|
| 183 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00013-of-00026.safetensors",
|
| 184 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00013-of-00026.safetensors",
|
| 185 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00013-of-00026.safetensors",
|
| 186 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00013-of-00026.safetensors",
|
| 187 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00013-of-00026.safetensors",
|
| 188 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00012-of-00026.safetensors",
|
| 189 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00012-of-00026.safetensors",
|
| 190 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00013-of-00026.safetensors",
|
| 191 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00012-of-00026.safetensors",
|
| 192 |
+
"model.language_model.layers.18.mlp.experts.down_proj": "model-00012-of-00026.safetensors",
|
| 193 |
+
"model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00013-of-00026.safetensors",
|
| 194 |
+
"model.language_model.layers.18.mlp.gate.weight": "model-00013-of-00026.safetensors",
|
| 195 |
+
"model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
|
| 196 |
+
"model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
|
| 197 |
+
"model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
|
| 198 |
+
"model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
|
| 199 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
|
| 200 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00013-of-00026.safetensors",
|
| 201 |
+
"model.language_model.layers.19.mlp.experts.down_proj": "model-00013-of-00026.safetensors",
|
| 202 |
+
"model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00012-of-00026.safetensors",
|
| 203 |
+
"model.language_model.layers.19.mlp.gate.weight": "model-00013-of-00026.safetensors",
|
| 204 |
+
"model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
|
| 205 |
+
"model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
|
| 206 |
+
"model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
|
| 207 |
+
"model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
|
| 208 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
|
| 209 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00013-of-00026.safetensors",
|
| 210 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00012-of-00026.safetensors",
|
| 211 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00012-of-00026.safetensors",
|
| 212 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00013-of-00026.safetensors",
|
| 213 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00012-of-00026.safetensors",
|
| 214 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00012-of-00026.safetensors",
|
| 215 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00003-of-00026.safetensors",
|
| 216 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00003-of-00026.safetensors",
|
| 217 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00003-of-00026.safetensors",
|
| 218 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00003-of-00026.safetensors",
|
| 219 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00003-of-00026.safetensors",
|
| 220 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00003-of-00026.safetensors",
|
| 221 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00003-of-00026.safetensors",
|
| 222 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00003-of-00026.safetensors",
|
| 223 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00003-of-00026.safetensors",
|
| 224 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00003-of-00026.safetensors",
|
| 225 |
+
"model.language_model.layers.2.mlp.experts.down_proj": "model-00003-of-00026.safetensors",
|
| 226 |
+
"model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00003-of-00026.safetensors",
|
| 227 |
+
"model.language_model.layers.2.mlp.gate.weight": "model-00003-of-00026.safetensors",
|
| 228 |
+
"model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00003-of-00026.safetensors",
|
| 229 |
+
"model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00003-of-00026.safetensors",
|
| 230 |
+
"model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00003-of-00026.safetensors",
|
| 231 |
+
"model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00003-of-00026.safetensors",
|
| 232 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00003-of-00026.safetensors",
|
| 233 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00015-of-00026.safetensors",
|
| 234 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00015-of-00026.safetensors",
|
| 235 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
|
| 236 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
|
| 237 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
|
| 238 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
|
| 239 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
|
| 240 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
|
| 241 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
|
| 242 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
|
| 243 |
+
"model.language_model.layers.20.mlp.experts.down_proj": "model-00014-of-00026.safetensors",
|
| 244 |
+
"model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00014-of-00026.safetensors",
|
| 245 |
+
"model.language_model.layers.20.mlp.gate.weight": "model-00015-of-00026.safetensors",
|
| 246 |
+
"model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
|
| 247 |
+
"model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
|
| 248 |
+
"model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
|
| 249 |
+
"model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
|
| 250 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
|
| 251 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00015-of-00026.safetensors",
|
| 252 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00015-of-00026.safetensors",
|
| 253 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
|
| 254 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
|
| 255 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
|
| 256 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
|
| 257 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
|
| 258 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
|
| 259 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
|
| 260 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
|
| 261 |
+
"model.language_model.layers.21.mlp.experts.down_proj": "model-00014-of-00026.safetensors",
|
| 262 |
+
"model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00015-of-00026.safetensors",
|
| 263 |
+
"model.language_model.layers.21.mlp.gate.weight": "model-00015-of-00026.safetensors",
|
| 264 |
+
"model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
|
| 265 |
+
"model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
|
| 266 |
+
"model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
|
| 267 |
+
"model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
|
| 268 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
|
| 269 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00015-of-00026.safetensors",
|
| 270 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00015-of-00026.safetensors",
|
| 271 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
|
| 272 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
|
| 273 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
|
| 274 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
|
| 275 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
|
| 276 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
|
| 277 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
|
| 278 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
|
| 279 |
+
"model.language_model.layers.22.mlp.experts.down_proj": "model-00015-of-00026.safetensors",
|
| 280 |
+
"model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00014-of-00026.safetensors",
|
| 281 |
+
"model.language_model.layers.22.mlp.gate.weight": "model-00015-of-00026.safetensors",
|
| 282 |
+
"model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
|
| 283 |
+
"model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
|
| 284 |
+
"model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
|
| 285 |
+
"model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
|
| 286 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
|
| 287 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00017-of-00026.safetensors",
|
| 288 |
+
"model.language_model.layers.23.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
|
| 289 |
+
"model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00016-of-00026.safetensors",
|
| 290 |
+
"model.language_model.layers.23.mlp.gate.weight": "model-00017-of-00026.safetensors",
|
| 291 |
+
"model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
|
| 292 |
+
"model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
|
| 293 |
+
"model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
|
| 294 |
+
"model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
|
| 295 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
|
| 296 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00017-of-00026.safetensors",
|
| 297 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00016-of-00026.safetensors",
|
| 298 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00016-of-00026.safetensors",
|
| 299 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00017-of-00026.safetensors",
|
| 300 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00016-of-00026.safetensors",
|
| 301 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00016-of-00026.safetensors",
|
| 302 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00017-of-00026.safetensors",
|
| 303 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00017-of-00026.safetensors",
|
| 304 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00017-of-00026.safetensors",
|
| 305 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00017-of-00026.safetensors",
|
| 306 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00017-of-00026.safetensors",
|
| 307 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00017-of-00026.safetensors",
|
| 308 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00016-of-00026.safetensors",
|
| 309 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00016-of-00026.safetensors",
|
| 310 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00017-of-00026.safetensors",
|
| 311 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00016-of-00026.safetensors",
|
| 312 |
+
"model.language_model.layers.24.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
|
| 313 |
+
"model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00016-of-00026.safetensors",
|
| 314 |
+
"model.language_model.layers.24.mlp.gate.weight": "model-00017-of-00026.safetensors",
|
| 315 |
+
"model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
|
| 316 |
+
"model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
|
| 317 |
+
"model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
|
| 318 |
+
"model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
|
| 319 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
|
| 320 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00017-of-00026.safetensors",
|
| 321 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00017-of-00026.safetensors",
|
| 322 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00017-of-00026.safetensors",
|
| 323 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00017-of-00026.safetensors",
|
| 324 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00017-of-00026.safetensors",
|
| 325 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00017-of-00026.safetensors",
|
| 326 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00016-of-00026.safetensors",
|
| 327 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00016-of-00026.safetensors",
|
| 328 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00017-of-00026.safetensors",
|
| 329 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00016-of-00026.safetensors",
|
| 330 |
+
"model.language_model.layers.25.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
|
| 331 |
+
"model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00017-of-00026.safetensors",
|
| 332 |
+
"model.language_model.layers.25.mlp.gate.weight": "model-00017-of-00026.safetensors",
|
| 333 |
+
"model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
|
| 334 |
+
"model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
|
| 335 |
+
"model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
|
| 336 |
+
"model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
|
| 337 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
|
| 338 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00019-of-00026.safetensors",
|
| 339 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00019-of-00026.safetensors",
|
| 340 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00019-of-00026.safetensors",
|
| 341 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00019-of-00026.safetensors",
|
| 342 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00019-of-00026.safetensors",
|
| 343 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00019-of-00026.safetensors",
|
| 344 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00018-of-00026.safetensors",
|
| 345 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00018-of-00026.safetensors",
|
| 346 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00019-of-00026.safetensors",
|
| 347 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00018-of-00026.safetensors",
|
| 348 |
+
"model.language_model.layers.26.mlp.experts.down_proj": "model-00019-of-00026.safetensors",
|
| 349 |
+
"model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
|
| 350 |
+
"model.language_model.layers.26.mlp.gate.weight": "model-00019-of-00026.safetensors",
|
| 351 |
+
"model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
|
| 352 |
+
"model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
|
| 353 |
+
"model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
|
| 354 |
+
"model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
|
| 355 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
|
| 356 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00019-of-00026.safetensors",
|
| 357 |
+
"model.language_model.layers.27.mlp.experts.down_proj": "model-00019-of-00026.safetensors",
|
| 358 |
+
"model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
|
| 359 |
+
"model.language_model.layers.27.mlp.gate.weight": "model-00019-of-00026.safetensors",
|
| 360 |
+
"model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
|
| 361 |
+
"model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
|
| 362 |
+
"model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
|
| 363 |
+
"model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
|
| 364 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
|
| 365 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00019-of-00026.safetensors",
|
| 366 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00018-of-00026.safetensors",
|
| 367 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00018-of-00026.safetensors",
|
| 368 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00019-of-00026.safetensors",
|
| 369 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00018-of-00026.safetensors",
|
| 370 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00018-of-00026.safetensors",
|
| 371 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00019-of-00026.safetensors",
|
| 372 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00019-of-00026.safetensors",
|
| 373 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00019-of-00026.safetensors",
|
| 374 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00019-of-00026.safetensors",
|
| 375 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00019-of-00026.safetensors",
|
| 376 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00019-of-00026.safetensors",
|
| 377 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00018-of-00026.safetensors",
|
| 378 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00018-of-00026.safetensors",
|
| 379 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00019-of-00026.safetensors",
|
| 380 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00018-of-00026.safetensors",
|
| 381 |
+
"model.language_model.layers.28.mlp.experts.down_proj": "model-00018-of-00026.safetensors",
|
| 382 |
+
"model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
|
| 383 |
+
"model.language_model.layers.28.mlp.gate.weight": "model-00019-of-00026.safetensors",
|
| 384 |
+
"model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
|
| 385 |
+
"model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
|
| 386 |
+
"model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
|
| 387 |
+
"model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
|
| 388 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
|
| 389 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00021-of-00026.safetensors",
|
| 390 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00021-of-00026.safetensors",
|
| 391 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00021-of-00026.safetensors",
|
| 392 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00021-of-00026.safetensors",
|
| 393 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00021-of-00026.safetensors",
|
| 394 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00021-of-00026.safetensors",
|
| 395 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00020-of-00026.safetensors",
|
| 396 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00020-of-00026.safetensors",
|
| 397 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00021-of-00026.safetensors",
|
| 398 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00020-of-00026.safetensors",
|
| 399 |
+
"model.language_model.layers.29.mlp.experts.down_proj": "model-00020-of-00026.safetensors",
|
| 400 |
+
"model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00021-of-00026.safetensors",
|
| 401 |
+
"model.language_model.layers.29.mlp.gate.weight": "model-00021-of-00026.safetensors",
|
| 402 |
+
"model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
|
| 403 |
+
"model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
|
| 404 |
+
"model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
|
| 405 |
+
"model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
|
| 406 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
|
| 407 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00003-of-00026.safetensors",
|
| 408 |
+
"model.language_model.layers.3.mlp.experts.down_proj": "model-00003-of-00026.safetensors",
|
| 409 |
+
"model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00003-of-00026.safetensors",
|
| 410 |
+
"model.language_model.layers.3.mlp.gate.weight": "model-00003-of-00026.safetensors",
|
| 411 |
+
"model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00003-of-00026.safetensors",
|
| 412 |
+
"model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00003-of-00026.safetensors",
|
| 413 |
+
"model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00003-of-00026.safetensors",
|
| 414 |
+
"model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00003-of-00026.safetensors",
|
| 415 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00003-of-00026.safetensors",
|
| 416 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00003-of-00026.safetensors",
|
| 417 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00003-of-00026.safetensors",
|
| 418 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00003-of-00026.safetensors",
|
| 419 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00003-of-00026.safetensors",
|
| 420 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00003-of-00026.safetensors",
|
| 421 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00003-of-00026.safetensors",
|
| 422 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00021-of-00026.safetensors",
|
| 423 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00021-of-00026.safetensors",
|
| 424 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00021-of-00026.safetensors",
|
| 425 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00021-of-00026.safetensors",
|
| 426 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00021-of-00026.safetensors",
|
| 427 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00021-of-00026.safetensors",
|
| 428 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00020-of-00026.safetensors",
|
| 429 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00020-of-00026.safetensors",
|
| 430 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00021-of-00026.safetensors",
|
| 431 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00020-of-00026.safetensors",
|
| 432 |
+
"model.language_model.layers.30.mlp.experts.down_proj": "model-00021-of-00026.safetensors",
|
| 433 |
+
"model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00020-of-00026.safetensors",
|
| 434 |
+
"model.language_model.layers.30.mlp.gate.weight": "model-00021-of-00026.safetensors",
|
| 435 |
+
"model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
|
| 436 |
+
"model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
|
| 437 |
+
"model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
|
| 438 |
+
"model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
|
| 439 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
|
| 440 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00021-of-00026.safetensors",
|
| 441 |
+
"model.language_model.layers.31.mlp.experts.down_proj": "model-00020-of-00026.safetensors",
|
| 442 |
+
"model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00020-of-00026.safetensors",
|
| 443 |
+
"model.language_model.layers.31.mlp.gate.weight": "model-00021-of-00026.safetensors",
|
| 444 |
+
"model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
|
| 445 |
+
"model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
|
| 446 |
+
"model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
|
| 447 |
+
"model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
|
| 448 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
|
| 449 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00021-of-00026.safetensors",
|
| 450 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00020-of-00026.safetensors",
|
| 451 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00020-of-00026.safetensors",
|
| 452 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00021-of-00026.safetensors",
|
| 453 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00020-of-00026.safetensors",
|
| 454 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00020-of-00026.safetensors",
|
| 455 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00022-of-00026.safetensors",
|
| 456 |
+
"model.language_model.layers.32.linear_attn.A_log": "model-00022-of-00026.safetensors",
|
| 457 |
+
"model.language_model.layers.32.linear_attn.conv1d.weight": "model-00022-of-00026.safetensors",
|
| 458 |
+
"model.language_model.layers.32.linear_attn.dt_bias": "model-00022-of-00026.safetensors",
|
| 459 |
+
"model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00022-of-00026.safetensors",
|
| 460 |
+
"model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00022-of-00026.safetensors",
|
| 461 |
+
"model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00022-of-00026.safetensors",
|
| 462 |
+
"model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00022-of-00026.safetensors",
|
| 463 |
+
"model.language_model.layers.32.linear_attn.norm.weight": "model-00022-of-00026.safetensors",
|
| 464 |
+
"model.language_model.layers.32.linear_attn.out_proj.weight": "model-00022-of-00026.safetensors",
|
| 465 |
+
"model.language_model.layers.32.mlp.experts.down_proj": "model-00022-of-00026.safetensors",
|
| 466 |
+
"model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00022-of-00026.safetensors",
|
| 467 |
+
"model.language_model.layers.32.mlp.gate.weight": "model-00022-of-00026.safetensors",
|
| 468 |
+
"model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00022-of-00026.safetensors",
|
| 469 |
+
"model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00022-of-00026.safetensors",
|
| 470 |
+
"model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00022-of-00026.safetensors",
|
| 471 |
+
"model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00022-of-00026.safetensors",
|
| 472 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00022-of-00026.safetensors",
|
| 473 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00022-of-00026.safetensors",
|
| 474 |
+
"model.language_model.layers.33.linear_attn.A_log": "model-00022-of-00026.safetensors",
|
| 475 |
+
"model.language_model.layers.33.linear_attn.conv1d.weight": "model-00022-of-00026.safetensors",
|
| 476 |
+
"model.language_model.layers.33.linear_attn.dt_bias": "model-00022-of-00026.safetensors",
|
| 477 |
+
"model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00022-of-00026.safetensors",
|
| 478 |
+
"model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00022-of-00026.safetensors",
|
| 479 |
+
"model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00022-of-00026.safetensors",
|
| 480 |
+
"model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00022-of-00026.safetensors",
|
| 481 |
+
"model.language_model.layers.33.linear_attn.norm.weight": "model-00022-of-00026.safetensors",
|
| 482 |
+
"model.language_model.layers.33.linear_attn.out_proj.weight": "model-00022-of-00026.safetensors",
|
| 483 |
+
"model.language_model.layers.33.mlp.experts.down_proj": "model-00022-of-00026.safetensors",
|
| 484 |
+
"model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00022-of-00026.safetensors",
|
| 485 |
+
"model.language_model.layers.33.mlp.gate.weight": "model-00022-of-00026.safetensors",
|
| 486 |
+
"model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00022-of-00026.safetensors",
|
| 487 |
+
"model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00022-of-00026.safetensors",
|
| 488 |
+
"model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00022-of-00026.safetensors",
|
| 489 |
+
"model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00022-of-00026.safetensors",
|
| 490 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00022-of-00026.safetensors",
|
| 491 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00023-of-00026.safetensors",
|
| 492 |
+
"model.language_model.layers.34.linear_attn.A_log": "model-00023-of-00026.safetensors",
|
| 493 |
+
"model.language_model.layers.34.linear_attn.conv1d.weight": "model-00023-of-00026.safetensors",
|
| 494 |
+
"model.language_model.layers.34.linear_attn.dt_bias": "model-00023-of-00026.safetensors",
|
| 495 |
+
"model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00023-of-00026.safetensors",
|
| 496 |
+
"model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00023-of-00026.safetensors",
|
| 497 |
+
"model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00023-of-00026.safetensors",
|
| 498 |
+
"model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00023-of-00026.safetensors",
|
| 499 |
+
"model.language_model.layers.34.linear_attn.norm.weight": "model-00023-of-00026.safetensors",
|
| 500 |
+
"model.language_model.layers.34.linear_attn.out_proj.weight": "model-00023-of-00026.safetensors",
|
| 501 |
+
"model.language_model.layers.34.mlp.experts.down_proj": "model-00023-of-00026.safetensors",
|
| 502 |
+
"model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00023-of-00026.safetensors",
|
| 503 |
+
"model.language_model.layers.34.mlp.gate.weight": "model-00023-of-00026.safetensors",
|
| 504 |
+
"model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00023-of-00026.safetensors",
|
| 505 |
+
"model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00023-of-00026.safetensors",
|
| 506 |
+
"model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00023-of-00026.safetensors",
|
| 507 |
+
"model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00023-of-00026.safetensors",
|
| 508 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00023-of-00026.safetensors",
|
| 509 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00023-of-00026.safetensors",
|
| 510 |
+
"model.language_model.layers.35.mlp.experts.down_proj": "model-00023-of-00026.safetensors",
|
| 511 |
+
"model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00023-of-00026.safetensors",
|
| 512 |
+
"model.language_model.layers.35.mlp.gate.weight": "model-00023-of-00026.safetensors",
|
| 513 |
+
"model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00023-of-00026.safetensors",
|
| 514 |
+
"model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00023-of-00026.safetensors",
|
| 515 |
+
"model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00023-of-00026.safetensors",
|
| 516 |
+
"model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00023-of-00026.safetensors",
|
| 517 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00023-of-00026.safetensors",
|
| 518 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00023-of-00026.safetensors",
|
| 519 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00023-of-00026.safetensors",
|
| 520 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00023-of-00026.safetensors",
|
| 521 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00023-of-00026.safetensors",
|
| 522 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00023-of-00026.safetensors",
|
| 523 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00023-of-00026.safetensors",
|
| 524 |
+
"model.language_model.layers.36.input_layernorm.weight": "model-00024-of-00026.safetensors",
|
| 525 |
+
"model.language_model.layers.36.linear_attn.A_log": "model-00024-of-00026.safetensors",
|
| 526 |
+
"model.language_model.layers.36.linear_attn.conv1d.weight": "model-00024-of-00026.safetensors",
|
| 527 |
+
"model.language_model.layers.36.linear_attn.dt_bias": "model-00024-of-00026.safetensors",
|
| 528 |
+
"model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00024-of-00026.safetensors",
|
| 529 |
+
"model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00024-of-00026.safetensors",
|
| 530 |
+
"model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00024-of-00026.safetensors",
|
| 531 |
+
"model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00024-of-00026.safetensors",
|
| 532 |
+
"model.language_model.layers.36.linear_attn.norm.weight": "model-00024-of-00026.safetensors",
|
| 533 |
+
"model.language_model.layers.36.linear_attn.out_proj.weight": "model-00024-of-00026.safetensors",
|
| 534 |
+
"model.language_model.layers.36.mlp.experts.down_proj": "model-00024-of-00026.safetensors",
|
| 535 |
+
"model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00024-of-00026.safetensors",
|
| 536 |
+
"model.language_model.layers.36.mlp.gate.weight": "model-00024-of-00026.safetensors",
|
| 537 |
+
"model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00024-of-00026.safetensors",
|
| 538 |
+
"model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00024-of-00026.safetensors",
|
| 539 |
+
"model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00024-of-00026.safetensors",
|
| 540 |
+
"model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00024-of-00026.safetensors",
|
| 541 |
+
"model.language_model.layers.36.post_attention_layernorm.weight": "model-00024-of-00026.safetensors",
|
| 542 |
+
"model.language_model.layers.37.input_layernorm.weight": "model-00024-of-00026.safetensors",
|
| 543 |
+
"model.language_model.layers.37.linear_attn.A_log": "model-00024-of-00026.safetensors",
|
| 544 |
+
"model.language_model.layers.37.linear_attn.conv1d.weight": "model-00024-of-00026.safetensors",
|
| 545 |
+
"model.language_model.layers.37.linear_attn.dt_bias": "model-00024-of-00026.safetensors",
|
| 546 |
+
"model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00024-of-00026.safetensors",
|
| 547 |
+
"model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00024-of-00026.safetensors",
|
| 548 |
+
"model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00024-of-00026.safetensors",
|
| 549 |
+
"model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00024-of-00026.safetensors",
|
| 550 |
+
"model.language_model.layers.37.linear_attn.norm.weight": "model-00024-of-00026.safetensors",
|
| 551 |
+
"model.language_model.layers.37.linear_attn.out_proj.weight": "model-00024-of-00026.safetensors",
|
| 552 |
+
"model.language_model.layers.37.mlp.experts.down_proj": "model-00024-of-00026.safetensors",
|
| 553 |
+
"model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00024-of-00026.safetensors",
|
| 554 |
+
"model.language_model.layers.37.mlp.gate.weight": "model-00024-of-00026.safetensors",
|
| 555 |
+
"model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00024-of-00026.safetensors",
|
| 556 |
+
"model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00024-of-00026.safetensors",
|
| 557 |
+
"model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00024-of-00026.safetensors",
|
| 558 |
+
"model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00024-of-00026.safetensors",
|
| 559 |
+
"model.language_model.layers.37.post_attention_layernorm.weight": "model-00024-of-00026.safetensors",
|
| 560 |
+
"model.language_model.layers.38.input_layernorm.weight": "model-00025-of-00026.safetensors",
|
| 561 |
+
"model.language_model.layers.38.linear_attn.A_log": "model-00025-of-00026.safetensors",
|
| 562 |
+
"model.language_model.layers.38.linear_attn.conv1d.weight": "model-00025-of-00026.safetensors",
|
| 563 |
+
"model.language_model.layers.38.linear_attn.dt_bias": "model-00025-of-00026.safetensors",
|
| 564 |
+
"model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00025-of-00026.safetensors",
|
| 565 |
+
"model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00025-of-00026.safetensors",
|
| 566 |
+
"model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00025-of-00026.safetensors",
|
| 567 |
+
"model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00025-of-00026.safetensors",
|
| 568 |
+
"model.language_model.layers.38.linear_attn.norm.weight": "model-00025-of-00026.safetensors",
|
| 569 |
+
"model.language_model.layers.38.linear_attn.out_proj.weight": "model-00025-of-00026.safetensors",
|
| 570 |
+
"model.language_model.layers.38.mlp.experts.down_proj": "model-00025-of-00026.safetensors",
|
| 571 |
+
"model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
|
| 572 |
+
"model.language_model.layers.38.mlp.gate.weight": "model-00025-of-00026.safetensors",
|
| 573 |
+
"model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00025-of-00026.safetensors",
|
| 574 |
+
"model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00025-of-00026.safetensors",
|
| 575 |
+
"model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00025-of-00026.safetensors",
|
| 576 |
+
"model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00025-of-00026.safetensors",
|
| 577 |
+
"model.language_model.layers.38.post_attention_layernorm.weight": "model-00025-of-00026.safetensors",
|
| 578 |
+
"model.language_model.layers.39.input_layernorm.weight": "model-00026-of-00026.safetensors",
|
| 579 |
+
"model.language_model.layers.39.mlp.experts.down_proj": "model-00026-of-00026.safetensors",
|
| 580 |
+
"model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
|
| 581 |
+
"model.language_model.layers.39.mlp.gate.weight": "model-00026-of-00026.safetensors",
|
| 582 |
+
"model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00026-of-00026.safetensors",
|
| 583 |
+
"model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00026-of-00026.safetensors",
|
| 584 |
+
"model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00026-of-00026.safetensors",
|
| 585 |
+
"model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00026-of-00026.safetensors",
|
| 586 |
+
"model.language_model.layers.39.post_attention_layernorm.weight": "model-00026-of-00026.safetensors",
|
| 587 |
+
"model.language_model.layers.39.self_attn.k_norm.weight": "model-00026-of-00026.safetensors",
|
| 588 |
+
"model.language_model.layers.39.self_attn.k_proj.weight": "model-00026-of-00026.safetensors",
|
| 589 |
+
"model.language_model.layers.39.self_attn.o_proj.weight": "model-00026-of-00026.safetensors",
|
| 590 |
+
"model.language_model.layers.39.self_attn.q_norm.weight": "model-00026-of-00026.safetensors",
|
| 591 |
+
"model.language_model.layers.39.self_attn.q_proj.weight": "model-00026-of-00026.safetensors",
|
| 592 |
+
"model.language_model.layers.39.self_attn.v_proj.weight": "model-00026-of-00026.safetensors",
|
| 593 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00004-of-00026.safetensors",
|
| 594 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00004-of-00026.safetensors",
|
| 595 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00004-of-00026.safetensors",
|
| 596 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00004-of-00026.safetensors",
|
| 597 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00004-of-00026.safetensors",
|
| 598 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00004-of-00026.safetensors",
|
| 599 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00004-of-00026.safetensors",
|
| 600 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00004-of-00026.safetensors",
|
| 601 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00004-of-00026.safetensors",
|
| 602 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00004-of-00026.safetensors",
|
| 603 |
+
"model.language_model.layers.4.mlp.experts.down_proj": "model-00004-of-00026.safetensors",
|
| 604 |
+
"model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00004-of-00026.safetensors",
|
| 605 |
+
"model.language_model.layers.4.mlp.gate.weight": "model-00004-of-00026.safetensors",
|
| 606 |
+
"model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00004-of-00026.safetensors",
|
| 607 |
+
"model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00004-of-00026.safetensors",
|
| 608 |
+
"model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00004-of-00026.safetensors",
|
| 609 |
+
"model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00004-of-00026.safetensors",
|
| 610 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00004-of-00026.safetensors",
|
| 611 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00004-of-00026.safetensors",
|
| 612 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00004-of-00026.safetensors",
|
| 613 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00004-of-00026.safetensors",
|
| 614 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00004-of-00026.safetensors",
|
| 615 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00004-of-00026.safetensors",
|
| 616 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00004-of-00026.safetensors",
|
| 617 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00004-of-00026.safetensors",
|
| 618 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00004-of-00026.safetensors",
|
| 619 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00004-of-00026.safetensors",
|
| 620 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00004-of-00026.safetensors",
|
| 621 |
+
"model.language_model.layers.5.mlp.experts.down_proj": "model-00004-of-00026.safetensors",
|
| 622 |
+
"model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00004-of-00026.safetensors",
|
| 623 |
+
"model.language_model.layers.5.mlp.gate.weight": "model-00004-of-00026.safetensors",
|
| 624 |
+
"model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00004-of-00026.safetensors",
|
| 625 |
+
"model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00004-of-00026.safetensors",
|
| 626 |
+
"model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00004-of-00026.safetensors",
|
| 627 |
+
"model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00004-of-00026.safetensors",
|
| 628 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00004-of-00026.safetensors",
|
| 629 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00005-of-00026.safetensors",
|
| 630 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00005-of-00026.safetensors",
|
| 631 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00005-of-00026.safetensors",
|
| 632 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00005-of-00026.safetensors",
|
| 633 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00005-of-00026.safetensors",
|
| 634 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00005-of-00026.safetensors",
|
| 635 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00005-of-00026.safetensors",
|
| 636 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00005-of-00026.safetensors",
|
| 637 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00005-of-00026.safetensors",
|
| 638 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00005-of-00026.safetensors",
|
| 639 |
+
"model.language_model.layers.6.mlp.experts.down_proj": "model-00005-of-00026.safetensors",
|
| 640 |
+
"model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00005-of-00026.safetensors",
|
| 641 |
+
"model.language_model.layers.6.mlp.gate.weight": "model-00005-of-00026.safetensors",
|
| 642 |
+
"model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00005-of-00026.safetensors",
|
| 643 |
+
"model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00005-of-00026.safetensors",
|
| 644 |
+
"model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00005-of-00026.safetensors",
|
| 645 |
+
"model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00005-of-00026.safetensors",
|
| 646 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00005-of-00026.safetensors",
|
| 647 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00005-of-00026.safetensors",
|
| 648 |
+
"model.language_model.layers.7.mlp.experts.down_proj": "model-00005-of-00026.safetensors",
|
| 649 |
+
"model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00005-of-00026.safetensors",
|
| 650 |
+
"model.language_model.layers.7.mlp.gate.weight": "model-00005-of-00026.safetensors",
|
| 651 |
+
"model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00005-of-00026.safetensors",
|
| 652 |
+
"model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00005-of-00026.safetensors",
|
| 653 |
+
"model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00005-of-00026.safetensors",
|
| 654 |
+
"model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00005-of-00026.safetensors",
|
| 655 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00005-of-00026.safetensors",
|
| 656 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00005-of-00026.safetensors",
|
| 657 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00005-of-00026.safetensors",
|
| 658 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00005-of-00026.safetensors",
|
| 659 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00005-of-00026.safetensors",
|
| 660 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00005-of-00026.safetensors",
|
| 661 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00005-of-00026.safetensors",
|
| 662 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00007-of-00026.safetensors",
|
| 663 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00007-of-00026.safetensors",
|
| 664 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
|
| 665 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
|
| 666 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
|
| 667 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
|
| 668 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
|
| 669 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
|
| 670 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
|
| 671 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
|
| 672 |
+
"model.language_model.layers.8.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
|
| 673 |
+
"model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00006-of-00026.safetensors",
|
| 674 |
+
"model.language_model.layers.8.mlp.gate.weight": "model-00007-of-00026.safetensors",
|
| 675 |
+
"model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
|
| 676 |
+
"model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
|
| 677 |
+
"model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
|
| 678 |
+
"model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
|
| 679 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
|
| 680 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00007-of-00026.safetensors",
|
| 681 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00007-of-00026.safetensors",
|
| 682 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
|
| 683 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
|
| 684 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
|
| 685 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
|
| 686 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
|
| 687 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
|
| 688 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
|
| 689 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
|
| 690 |
+
"model.language_model.layers.9.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
|
| 691 |
+
"model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00006-of-00026.safetensors",
|
| 692 |
+
"model.language_model.layers.9.mlp.gate.weight": "model-00007-of-00026.safetensors",
|
| 693 |
+
"model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
|
| 694 |
+
"model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
|
| 695 |
+
"model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
|
| 696 |
+
"model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
|
| 697 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
|
| 698 |
+
"model.language_model.norm.weight": "model-00026-of-00026.safetensors",
|
| 699 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 700 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 701 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 702 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 703 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 704 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
|
| 705 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 706 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
|
| 707 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00026.safetensors",
|
| 708 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00026.safetensors",
|
| 709 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00026.safetensors",
|
| 710 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00026.safetensors",
|
| 711 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 712 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 713 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 714 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 715 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 716 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
|
| 717 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 718 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
|
| 719 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00026.safetensors",
|
| 720 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00026.safetensors",
|
| 721 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00026.safetensors",
|
| 722 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00026.safetensors",
|
| 723 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 724 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 725 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 726 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 727 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 728 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
|
| 729 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 730 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
|
| 731 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00026.safetensors",
|
| 732 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00026.safetensors",
|
| 733 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00026.safetensors",
|
| 734 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00026.safetensors",
|
| 735 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 736 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 737 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 738 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 739 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 740 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
|
| 741 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 742 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
|
| 743 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00026.safetensors",
|
| 744 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00026.safetensors",
|
| 745 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00026.safetensors",
|
| 746 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00026.safetensors",
|
| 747 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 748 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 749 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 750 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 751 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 752 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
|
| 753 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 754 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
|
| 755 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00026.safetensors",
|
| 756 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00026.safetensors",
|
| 757 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00026.safetensors",
|
| 758 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00026.safetensors",
|
| 759 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 760 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 761 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 762 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 763 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 764 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 765 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 766 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 767 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00026.safetensors",
|
| 768 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00026.safetensors",
|
| 769 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00026.safetensors",
|
| 770 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00026.safetensors",
|
| 771 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 772 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 773 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 774 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 775 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 776 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 777 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 778 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 779 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00026.safetensors",
|
| 780 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00026.safetensors",
|
| 781 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00026.safetensors",
|
| 782 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00026.safetensors",
|
| 783 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 784 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 785 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 786 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 787 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 788 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 789 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 790 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 791 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00026.safetensors",
|
| 792 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00026.safetensors",
|
| 793 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00026.safetensors",
|
| 794 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00026.safetensors",
|
| 795 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 796 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 797 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 798 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 799 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 800 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 801 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 802 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 803 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00026.safetensors",
|
| 804 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00026.safetensors",
|
| 805 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00026.safetensors",
|
| 806 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00026.safetensors",
|
| 807 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 808 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 809 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 810 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 811 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 812 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 813 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 814 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 815 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00026.safetensors",
|
| 816 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00026.safetensors",
|
| 817 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00026.safetensors",
|
| 818 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00026.safetensors",
|
| 819 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 820 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 821 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 822 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 823 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 824 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 825 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 826 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 827 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00026.safetensors",
|
| 828 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00026.safetensors",
|
| 829 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00026.safetensors",
|
| 830 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00026.safetensors",
|
| 831 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 832 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 833 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 834 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 835 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 836 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 837 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 838 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 839 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00026.safetensors",
|
| 840 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00026.safetensors",
|
| 841 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00026.safetensors",
|
| 842 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00026.safetensors",
|
| 843 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 844 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 845 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 846 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 847 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 848 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 849 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 850 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 851 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00026.safetensors",
|
| 852 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00026.safetensors",
|
| 853 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00026.safetensors",
|
| 854 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00026.safetensors",
|
| 855 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 856 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 857 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 858 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 859 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 860 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 861 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 862 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 863 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00026.safetensors",
|
| 864 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00026.safetensors",
|
| 865 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00026.safetensors",
|
| 866 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00026.safetensors",
|
| 867 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 868 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 869 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 870 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 871 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 872 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 873 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 874 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 875 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00026.safetensors",
|
| 876 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00026.safetensors",
|
| 877 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00026.safetensors",
|
| 878 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00026.safetensors",
|
| 879 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 880 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 881 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 882 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 883 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 884 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 885 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 886 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 887 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00026.safetensors",
|
| 888 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00026.safetensors",
|
| 889 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00026.safetensors",
|
| 890 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00026.safetensors",
|
| 891 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 892 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 893 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 894 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 895 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 896 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 897 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 898 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 899 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00026.safetensors",
|
| 900 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00026.safetensors",
|
| 901 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00026.safetensors",
|
| 902 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00026.safetensors",
|
| 903 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 904 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 905 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 906 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 907 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 908 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 909 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 910 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 911 |
+
"model.visual.blocks.24.norm1.bias": "model-00002-of-00026.safetensors",
|
| 912 |
+
"model.visual.blocks.24.norm1.weight": "model-00002-of-00026.safetensors",
|
| 913 |
+
"model.visual.blocks.24.norm2.bias": "model-00002-of-00026.safetensors",
|
| 914 |
+
"model.visual.blocks.24.norm2.weight": "model-00002-of-00026.safetensors",
|
| 915 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 916 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 917 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 918 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 919 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 920 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 921 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 922 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 923 |
+
"model.visual.blocks.25.norm1.bias": "model-00002-of-00026.safetensors",
|
| 924 |
+
"model.visual.blocks.25.norm1.weight": "model-00002-of-00026.safetensors",
|
| 925 |
+
"model.visual.blocks.25.norm2.bias": "model-00002-of-00026.safetensors",
|
| 926 |
+
"model.visual.blocks.25.norm2.weight": "model-00002-of-00026.safetensors",
|
| 927 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 928 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 929 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 930 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 931 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 932 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 933 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 934 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 935 |
+
"model.visual.blocks.26.norm1.bias": "model-00002-of-00026.safetensors",
|
| 936 |
+
"model.visual.blocks.26.norm1.weight": "model-00002-of-00026.safetensors",
|
| 937 |
+
"model.visual.blocks.26.norm2.bias": "model-00002-of-00026.safetensors",
|
| 938 |
+
"model.visual.blocks.26.norm2.weight": "model-00002-of-00026.safetensors",
|
| 939 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 940 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 941 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 942 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 943 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 944 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 945 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 946 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 947 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00026.safetensors",
|
| 948 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00026.safetensors",
|
| 949 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00026.safetensors",
|
| 950 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00026.safetensors",
|
| 951 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 952 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 953 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 954 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 955 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 956 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 957 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 958 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 959 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00026.safetensors",
|
| 960 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00026.safetensors",
|
| 961 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00026.safetensors",
|
| 962 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00026.safetensors",
|
| 963 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 964 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 965 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 966 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 967 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 968 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 969 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 970 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 971 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00026.safetensors",
|
| 972 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00026.safetensors",
|
| 973 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00026.safetensors",
|
| 974 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00026.safetensors",
|
| 975 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 976 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 977 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 978 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 979 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 980 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 981 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 982 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 983 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00026.safetensors",
|
| 984 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00026.safetensors",
|
| 985 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00026.safetensors",
|
| 986 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00026.safetensors",
|
| 987 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 988 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 989 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 990 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 991 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 992 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 993 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 994 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 995 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00026.safetensors",
|
| 996 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00026.safetensors",
|
| 997 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00026.safetensors",
|
| 998 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00026.safetensors",
|
| 999 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 1000 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 1001 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 1002 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 1003 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 1004 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 1005 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 1006 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 1007 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00026.safetensors",
|
| 1008 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00026.safetensors",
|
| 1009 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00026.safetensors",
|
| 1010 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00026.safetensors",
|
| 1011 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00026.safetensors",
|
| 1012 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00026.safetensors",
|
| 1013 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00026.safetensors",
|
| 1014 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00026.safetensors",
|
| 1015 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 1016 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
|
| 1017 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 1018 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
|
| 1019 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00026.safetensors",
|
| 1020 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00026.safetensors",
|
| 1021 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00026.safetensors",
|
| 1022 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00026.safetensors",
|
| 1023 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00026.safetensors",
|
| 1024 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00026.safetensors",
|
| 1025 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00026.safetensors",
|
| 1026 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00026.safetensors",
|
| 1027 |
+
"model.visual.merger.norm.bias": "model-00002-of-00026.safetensors",
|
| 1028 |
+
"model.visual.merger.norm.weight": "model-00002-of-00026.safetensors",
|
| 1029 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00026.safetensors",
|
| 1030 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00026.safetensors",
|
| 1031 |
+
"model.visual.pos_embed.weight": "model-00002-of-00026.safetensors",
|
| 1032 |
+
"mtp.fc.weight": "model-00026-of-00026.safetensors",
|
| 1033 |
+
"mtp.layers.0.input_layernorm.weight": "model-00026-of-00026.safetensors",
|
| 1034 |
+
"mtp.layers.0.mlp.experts.down_proj": "model-00026-of-00026.safetensors",
|
| 1035 |
+
"mtp.layers.0.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
|
| 1036 |
+
"mtp.layers.0.mlp.gate.weight": "model-00026-of-00026.safetensors",
|
| 1037 |
+
"mtp.layers.0.mlp.shared_expert.down_proj.weight": "model-00026-of-00026.safetensors",
|
| 1038 |
+
"mtp.layers.0.mlp.shared_expert.gate_proj.weight": "model-00026-of-00026.safetensors",
|
| 1039 |
+
"mtp.layers.0.mlp.shared_expert.up_proj.weight": "model-00026-of-00026.safetensors",
|
| 1040 |
+
"mtp.layers.0.mlp.shared_expert_gate.weight": "model-00026-of-00026.safetensors",
|
| 1041 |
+
"mtp.layers.0.post_attention_layernorm.weight": "model-00026-of-00026.safetensors",
|
| 1042 |
+
"mtp.layers.0.self_attn.k_norm.weight": "model-00026-of-00026.safetensors",
|
| 1043 |
+
"mtp.layers.0.self_attn.k_proj.weight": "model-00026-of-00026.safetensors",
|
| 1044 |
+
"mtp.layers.0.self_attn.o_proj.weight": "model-00026-of-00026.safetensors",
|
| 1045 |
+
"mtp.layers.0.self_attn.q_norm.weight": "model-00026-of-00026.safetensors",
|
| 1046 |
+
"mtp.layers.0.self_attn.q_proj.weight": "model-00026-of-00026.safetensors",
|
| 1047 |
+
"mtp.layers.0.self_attn.v_proj.weight": "model-00026-of-00026.safetensors",
|
| 1048 |
+
"mtp.norm.weight": "model-00026-of-00026.safetensors",
|
| 1049 |
+
"mtp.pre_fc_norm_embedding.weight": "model-00026-of-00026.safetensors",
|
| 1050 |
+
"mtp.pre_fc_norm_hidden.weight": "model-00026-of-00026.safetensors"
|
| 1051 |
+
}
|
| 1052 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 16777216,
|
| 25 |
+
"shortest_edge": 65536
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "Qwen3VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": true,
|
| 38 |
+
"fps": 2,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.5,
|
| 41 |
+
0.5,
|
| 42 |
+
0.5
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.5,
|
| 46 |
+
0.5,
|
| 47 |
+
0.5
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 16,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 25165824,
|
| 58 |
+
"shortest_edge": 4096
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|vision_pad|>",
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>",
|
| 33 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set num_sys = 0 %}\n{%- set merged_system = '' %}\n{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set first = render_content(messages[0].content, false, true)|trim %}\n {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}\n {%- set second = render_content(messages[1].content, false, true)|trim %}\n {%- set merged_system = first + '\\n' + second %}\n {%- set num_sys = 2 %}\n {%- else %}\n {%- set merged_system = first %}\n {%- set num_sys = 1 %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if merged_system %}\n {{- '\\n\\n' + merged_system }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if merged_system %}\n {{- '<|im_start|>system\\n' + merged_system + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if loop.index0 >= num_sys and message.role != \"system\" and message.role != \"developer\" %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is mapping %}\n {%- for args_name in tool_call.arguments %}\n {%- set args_value = tool_call.arguments[args_name] %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}\n{#- Unsloth fixes - developer role, tool calling #}"
|
| 34 |
+
}
|