Initial upload: MLX 4-bit quantized Qwen3-4B for ARC-AGI-2 with TTT pipeline
Browse files- README.md +235 -0
- config.json +78 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- model.safetensors.index.json +915 -0
- tokenizer.json +94 -0
- tokenizer_config.json +14 -0
README.md
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: sorokin/qwen3_4b_grids15_sft139
|
| 3 |
+
tags:
|
| 4 |
+
- mlx
|
| 5 |
+
- arc
|
| 6 |
+
- arc-agi
|
| 7 |
+
- arc-agi-2
|
| 8 |
+
- arc-prize
|
| 9 |
+
- puzzle-solving
|
| 10 |
+
- test-time-training
|
| 11 |
+
- qlora
|
| 12 |
+
- 4bit
|
| 13 |
+
license: apache-2.0
|
| 14 |
+
datasets:
|
| 15 |
+
- arc-prize-2026-arc-agi-2
|
| 16 |
+
library_name: mlx
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
# Qwen3-4B-ARC-MLX-4bit
|
| 21 |
+
|
| 22 |
+
An MLX 4-bit quantized version of [sorokin/qwen3_4b_grids15_sft139](https://www.kaggle.com/models/sorokin/qwen3_4b_grids15_sft139), a Qwen3-4B model fine-tuned for [ARC-AGI-2](https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-2) puzzle solving.
|
| 23 |
+
|
| 24 |
+
This model is designed to run on Apple Silicon (M1/M2/M3/M4) using the [MLX](https://github.com/ml-explore/mlx) framework and uses **test-time training (TTT)** -- per-puzzle QLoRA fine-tuning -- to solve ARC puzzles.
|
| 25 |
+
|
| 26 |
+
## Key Details
|
| 27 |
+
|
| 28 |
+
| Property | Value |
|
| 29 |
+
|----------|-------|
|
| 30 |
+
| Architecture | Qwen3-4B (36 layers, 2560 hidden, 32 heads) |
|
| 31 |
+
| Vocabulary | **16 tokens** (digits 0-9, newline, user/assistant/pad/eos) |
|
| 32 |
+
| Quantization | 4-bit (affine, group_size=64) via mlx-lm |
|
| 33 |
+
| Model Size | 1.9 GB |
|
| 34 |
+
| Base Model | sorokin/qwen3_4b_grids15_sft139 (Qwen3-4B fine-tuned on ~100K synthetic ARC grids) |
|
| 35 |
+
| Framework | MLX (Apple Silicon) |
|
| 36 |
+
|
| 37 |
+
## What is ARC-AGI-2?
|
| 38 |
+
|
| 39 |
+
[ARC-AGI-2](https://arcprize.org) (Abstraction and Reasoning Corpus) is a benchmark for measuring artificial general intelligence. Each puzzle consists of:
|
| 40 |
+
- **Training pairs**: 2-5 input/output grid examples demonstrating a transformation rule
|
| 41 |
+
- **Test input**: A new grid where the model must predict the output
|
| 42 |
+
- Grids are 2D arrays of colors (digits 0-9), up to 30x30
|
| 43 |
+
|
| 44 |
+
The challenge is that each puzzle has a **unique, never-before-seen rule** -- the model must infer the rule from just a few examples.
|
| 45 |
+
|
| 46 |
+
## How It Works: Test-Time Training (TTT)
|
| 47 |
+
|
| 48 |
+
This model cannot solve ARC puzzles via simple inference. It requires **per-puzzle fine-tuning**:
|
| 49 |
+
|
| 50 |
+
1. **Augment** the puzzle's training pairs (rotations, transpositions, color permutations) to create 8-16 training sequences
|
| 51 |
+
2. **QLoRA fine-tune** the model on these augmented examples (5 epochs, rank 32-128)
|
| 52 |
+
3. **Generate** multiple candidate outputs via sampling
|
| 53 |
+
4. **Vote** on the most common valid grid
|
| 54 |
+
5. **Reset** LoRA weights before the next puzzle
|
| 55 |
+
|
| 56 |
+
This approach was pioneered by the [NVARC team](https://github.com/1ytic/NVARC) (1st place ARC Prize 2025) and adapted here for MLX.
|
| 57 |
+
|
| 58 |
+
### Grid Encoding
|
| 59 |
+
|
| 60 |
+
Grids are encoded as digit strings with newlines, wrapped in a chat-like format:
|
| 61 |
+
|
| 62 |
+
```
|
| 63 |
+
<user_token>\n{input_grid}<eos_token><assistant_token>\n{output_grid}<eos_token>
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
The 16-token vocabulary maps directly: `0-9` for digits, `10` for newline, `11` for user, `12` for assistant, `13` for pad, `15` for eos.
|
| 67 |
+
|
| 68 |
+
## Usage with MLX
|
| 69 |
+
|
| 70 |
+
### Requirements
|
| 71 |
+
|
| 72 |
+
```bash
|
| 73 |
+
pip install mlx-lm>=0.31.0
|
| 74 |
+
```
|
| 75 |
+
|
| 76 |
+
### Quick Start
|
| 77 |
+
|
| 78 |
+
```python
|
| 79 |
+
import mlx.core as mx
|
| 80 |
+
import mlx.nn as nn
|
| 81 |
+
import mlx.optimizers as optim
|
| 82 |
+
import mlx_lm
|
| 83 |
+
from mlx_lm.tuner.utils import linear_to_lora_layers, remove_lora_layers
|
| 84 |
+
|
| 85 |
+
# Load model
|
| 86 |
+
model, tokenizer = mlx_lm.load("codelion/Qwen3-4B-ARC-MLX-4bit")
|
| 87 |
+
|
| 88 |
+
# Apply QLoRA
|
| 89 |
+
n_layers = len(model.model.layers)
|
| 90 |
+
linear_to_lora_layers(model, num_layers=n_layers, config={
|
| 91 |
+
'rank': 32, 'dropout': 0.0, 'scale': 10.0
|
| 92 |
+
})
|
| 93 |
+
mx.eval(model.parameters())
|
| 94 |
+
|
| 95 |
+
# Token IDs
|
| 96 |
+
USER, ASSISTANT, EOS, NEWLINE = 11, 12, 15, 10
|
| 97 |
+
|
| 98 |
+
def grid_to_tokens(grid):
|
| 99 |
+
tokens = []
|
| 100 |
+
for i, row in enumerate(grid):
|
| 101 |
+
tokens.extend(int(c) for c in row)
|
| 102 |
+
if i < len(grid) - 1:
|
| 103 |
+
tokens.append(NEWLINE)
|
| 104 |
+
return tokens
|
| 105 |
+
|
| 106 |
+
# Build training sequence from puzzle's training pairs
|
| 107 |
+
def build_sequence(train_pairs):
|
| 108 |
+
tokens = []
|
| 109 |
+
for pair in train_pairs:
|
| 110 |
+
tokens += [USER, NEWLINE] + grid_to_tokens(pair["input"]) + [EOS]
|
| 111 |
+
tokens += [ASSISTANT, NEWLINE] + grid_to_tokens(pair["output"]) + [EOS]
|
| 112 |
+
return tokens
|
| 113 |
+
|
| 114 |
+
# Example puzzle
|
| 115 |
+
puzzle = {
|
| 116 |
+
"train": [
|
| 117 |
+
{"input": [[1, 2], [3, 4]], "output": [[4, 3], [2, 1]]},
|
| 118 |
+
{"input": [[5, 6], [7, 8]], "output": [[8, 7], [6, 5]]},
|
| 119 |
+
],
|
| 120 |
+
"test": [{"input": [[9, 0], [1, 2]]}]
|
| 121 |
+
}
|
| 122 |
+
|
| 123 |
+
# --- Test-Time Training ---
|
| 124 |
+
train_tokens = build_sequence(puzzle["train"])
|
| 125 |
+
labels = [-100] * len(train_tokens)
|
| 126 |
+
|
| 127 |
+
# Unmask assistant turns only
|
| 128 |
+
i = 0
|
| 129 |
+
while i < len(train_tokens):
|
| 130 |
+
if train_tokens[i] == ASSISTANT:
|
| 131 |
+
i += 2 # skip ASSISTANT + NEWLINE
|
| 132 |
+
while i < len(train_tokens) and train_tokens[i] != EOS:
|
| 133 |
+
labels[i] = train_tokens[i]
|
| 134 |
+
i += 1
|
| 135 |
+
if i < len(train_tokens):
|
| 136 |
+
labels[i] = train_tokens[i] # EOS
|
| 137 |
+
i += 1
|
| 138 |
+
|
| 139 |
+
optimizer = optim.Adam(learning_rate=5e-5)
|
| 140 |
+
for epoch in range(5):
|
| 141 |
+
inp = mx.array([train_tokens[:-1]])
|
| 142 |
+
tgt = mx.array([labels[1:]])
|
| 143 |
+
|
| 144 |
+
def loss_fn(model):
|
| 145 |
+
out = model(inp)
|
| 146 |
+
if isinstance(out, tuple): out = out[0]
|
| 147 |
+
logits = out.reshape(-1, out.shape[-1])
|
| 148 |
+
target = tgt.reshape(-1)
|
| 149 |
+
mask = target != -100
|
| 150 |
+
ce = nn.losses.cross_entropy(logits, target, reduction='none')
|
| 151 |
+
return (ce * mask).sum() / mask.sum()
|
| 152 |
+
|
| 153 |
+
loss, grads = nn.value_and_grad(model, loss_fn)(model)
|
| 154 |
+
optimizer.update(model, grads)
|
| 155 |
+
mx.eval(model.parameters(), optimizer.state)
|
| 156 |
+
print(f"Epoch {epoch}: loss={loss.item():.4f}")
|
| 157 |
+
|
| 158 |
+
# --- Generate ---
|
| 159 |
+
prompt = build_sequence(puzzle["train"])
|
| 160 |
+
prompt += [USER, NEWLINE] + grid_to_tokens(puzzle["test"][0]["input"]) + [EOS]
|
| 161 |
+
prompt += [ASSISTANT, NEWLINE]
|
| 162 |
+
|
| 163 |
+
sampler = mlx_lm.sample_utils.make_sampler(temp=0.5)
|
| 164 |
+
response = mlx_lm.generate(model, tokenizer, prompt=prompt, max_tokens=200,
|
| 165 |
+
sampler=sampler, verbose=False)
|
| 166 |
+
print(f"Output: {response}")
|
| 167 |
+
|
| 168 |
+
# --- Reset for next puzzle ---
|
| 169 |
+
remove_lora_layers(model)
|
| 170 |
+
linear_to_lora_layers(model, num_layers=n_layers, config={
|
| 171 |
+
'rank': 32, 'dropout': 0.0, 'scale': 10.0
|
| 172 |
+
})
|
| 173 |
+
mx.eval(model.parameters())
|
| 174 |
+
```
|
| 175 |
+
|
| 176 |
+
### Full Pipeline
|
| 177 |
+
|
| 178 |
+
See [mlx_nvarc.py](https://github.com/codelion/proofs/blob/main/arc2/mlx_nvarc.py) for the complete evaluation pipeline with augmentation, multi-sample generation, and voting.
|
| 179 |
+
|
| 180 |
+
## Results
|
| 181 |
+
|
| 182 |
+
### ARC-AGI-2 Training Set (304 tasks, grids up to 10x10)
|
| 183 |
+
|
| 184 |
+
| Metric | Value |
|
| 185 |
+
|--------|-------|
|
| 186 |
+
| **Tasks evaluated** | 304 |
|
| 187 |
+
| **Test instances** | 328 |
|
| 188 |
+
| **Correct** | 192 |
|
| 189 |
+
| **Accuracy** | **58.5%** |
|
| 190 |
+
| Avg time per task | 479s (~8 min) |
|
| 191 |
+
| Total compute time | 40.5 hours |
|
| 192 |
+
|
| 193 |
+
This is an unofficial score on the ARC-AGI-2 training split (grids up to 10x10). For reference, the [ARC-AGI-2 Kaggle leaderboard](https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-2/leaderboard) top scores are around 12% on the hidden test set, which contains harder puzzles with larger grids (up to 30x30). Training set tasks are generally easier, so this score is not directly comparable to leaderboard scores.
|
| 194 |
+
|
| 195 |
+
| Split | First 152 tasks | Last 152 tasks | Combined |
|
| 196 |
+
|-------|----------------|----------------|----------|
|
| 197 |
+
| Correct / Total | 94/163 | 98/165 | 192/328 |
|
| 198 |
+
| Accuracy | 57.7% | 59.4% | 58.5% |
|
| 199 |
+
|
| 200 |
+
The consistent accuracy across both halves (run independently) validates the reproducibility of the results.
|
| 201 |
+
|
| 202 |
+
### Configuration
|
| 203 |
+
|
| 204 |
+
- **LoRA rank**: 32
|
| 205 |
+
- **Learning rate**: 5e-5
|
| 206 |
+
- **TTT epochs**: 5
|
| 207 |
+
- **Augmentations**: 4 color permutations + 3 rotations + 2 transpositions
|
| 208 |
+
- **Samples per task**: 3 (+ 1 greedy)
|
| 209 |
+
- **Temperature**: 0.5
|
| 210 |
+
- **Hardware**: Apple M3 Max (36GB)
|
| 211 |
+
|
| 212 |
+
## Comparison with Original NVARC
|
| 213 |
+
|
| 214 |
+
| Aspect | NVARC (Kaggle) | This MLX Port |
|
| 215 |
+
|--------|---------------|---------------|
|
| 216 |
+
| Framework | PyTorch + Unsloth | MLX |
|
| 217 |
+
| Hardware | 2x NVIDIA T4 (32GB) | Apple Silicon (24-36GB) |
|
| 218 |
+
| Quantization | 4-bit via bitsandbytes | 4-bit via mlx-lm |
|
| 219 |
+
| LoRA rank | 256 | 32 |
|
| 220 |
+
| Decoding | Turbo DFS (tree search) | Sampling + voting |
|
| 221 |
+
| Speed per task | ~540s | ~480s |
|
| 222 |
+
|
| 223 |
+
## Limitations
|
| 224 |
+
|
| 225 |
+
- **Requires TTT**: The model produces garbage without per-puzzle fine-tuning
|
| 226 |
+
- **Speed**: Large grids (20x20+) with many training pairs can take over an hour on Apple Silicon
|
| 227 |
+
- **No DFS decoding**: The original NVARC uses a turbo DFS tree search for better candidate generation; this port uses simpler sampling + voting
|
| 228 |
+
- **Large grids**: Only evaluated on grids up to 10x10; larger grids are significantly slower and may have lower accuracy
|
| 229 |
+
|
| 230 |
+
## Acknowledgments
|
| 231 |
+
|
| 232 |
+
- [NVARC team](https://github.com/1ytic/NVARC) for the original ARC Prize 2025 winning solution
|
| 233 |
+
- [sorokin](https://www.kaggle.com/sorokin) for the pre-trained Qwen3-4B ARC model
|
| 234 |
+
- [MLX team](https://github.com/ml-explore/mlx) for the Apple Silicon ML framework
|
| 235 |
+
- [ARC Prize](https://arcprize.org) for the benchmark
|
config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 13,
|
| 8 |
+
"eos_token_id": 15,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2560,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 9728,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 262144,
|
| 53 |
+
"max_window_layers": 36,
|
| 54 |
+
"model_type": "qwen3",
|
| 55 |
+
"num_attention_heads": 32,
|
| 56 |
+
"num_hidden_layers": 36,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"quantization": {
|
| 59 |
+
"group_size": 64,
|
| 60 |
+
"bits": 4,
|
| 61 |
+
"mode": "affine"
|
| 62 |
+
},
|
| 63 |
+
"quantization_config": {
|
| 64 |
+
"group_size": 64,
|
| 65 |
+
"bits": 4,
|
| 66 |
+
"mode": "affine"
|
| 67 |
+
},
|
| 68 |
+
"rms_norm_eps": 1e-06,
|
| 69 |
+
"rope_scaling": null,
|
| 70 |
+
"rope_theta": 5000000,
|
| 71 |
+
"sliding_window": null,
|
| 72 |
+
"tie_word_embeddings": false,
|
| 73 |
+
"torch_dtype": "bfloat16",
|
| 74 |
+
"transformers_version": "4.53.3",
|
| 75 |
+
"use_cache": true,
|
| 76 |
+
"use_sliding_window": false,
|
| 77 |
+
"vocab_size": 16
|
| 78 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 13,
|
| 4 |
+
"eos_token_id": 15,
|
| 5 |
+
"transformers_version": "4.53.3"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:007cf011b6789de73fb90d6594c2fe01e4115cb6cf4c7f576e1592b4d64c9b8c
|
| 3 |
+
size 2044280880
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,915 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 2044178432,
|
| 4 |
+
"total_parameters": 3633593856
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.biases": "model.safetensors",
|
| 8 |
+
"lm_head.scales": "model.safetensors",
|
| 9 |
+
"lm_head.weight": "model.safetensors",
|
| 10 |
+
"model.embed_tokens.biases": "model.safetensors",
|
| 11 |
+
"model.embed_tokens.scales": "model.safetensors",
|
| 12 |
+
"model.embed_tokens.weight": "model.safetensors",
|
| 13 |
+
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 14 |
+
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
| 15 |
+
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 16 |
+
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 17 |
+
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
| 18 |
+
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 19 |
+
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 20 |
+
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
| 21 |
+
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 22 |
+
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 23 |
+
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.k_norm.weight": "model.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.q_norm.weight": "model.safetensors",
|
| 32 |
+
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 33 |
+
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 34 |
+
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 35 |
+
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 36 |
+
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 37 |
+
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 38 |
+
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 39 |
+
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
| 40 |
+
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 41 |
+
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 42 |
+
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
| 43 |
+
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 44 |
+
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 45 |
+
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
| 46 |
+
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 47 |
+
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 48 |
+
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 49 |
+
"model.layers.1.self_attn.k_norm.weight": "model.safetensors",
|
| 50 |
+
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 51 |
+
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 52 |
+
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 53 |
+
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
| 54 |
+
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 55 |
+
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 56 |
+
"model.layers.1.self_attn.q_norm.weight": "model.safetensors",
|
| 57 |
+
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 58 |
+
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 59 |
+
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 60 |
+
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 61 |
+
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 62 |
+
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 63 |
+
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 64 |
+
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
| 65 |
+
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 66 |
+
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 67 |
+
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
| 68 |
+
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 69 |
+
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 70 |
+
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
| 71 |
+
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 72 |
+
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 73 |
+
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 74 |
+
"model.layers.10.self_attn.k_norm.weight": "model.safetensors",
|
| 75 |
+
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 76 |
+
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 77 |
+
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 78 |
+
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
| 79 |
+
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 80 |
+
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 81 |
+
"model.layers.10.self_attn.q_norm.weight": "model.safetensors",
|
| 82 |
+
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 83 |
+
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 84 |
+
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 85 |
+
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 86 |
+
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 87 |
+
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 88 |
+
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 89 |
+
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
| 90 |
+
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 91 |
+
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 92 |
+
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
| 93 |
+
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 94 |
+
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 95 |
+
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
| 96 |
+
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 97 |
+
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 98 |
+
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 99 |
+
"model.layers.11.self_attn.k_norm.weight": "model.safetensors",
|
| 100 |
+
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 101 |
+
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 102 |
+
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 103 |
+
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
| 104 |
+
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 105 |
+
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 106 |
+
"model.layers.11.self_attn.q_norm.weight": "model.safetensors",
|
| 107 |
+
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 108 |
+
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 109 |
+
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 110 |
+
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 111 |
+
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 112 |
+
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 113 |
+
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 114 |
+
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
| 115 |
+
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 116 |
+
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 117 |
+
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
| 118 |
+
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 119 |
+
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 120 |
+
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
| 121 |
+
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 122 |
+
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 123 |
+
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 124 |
+
"model.layers.12.self_attn.k_norm.weight": "model.safetensors",
|
| 125 |
+
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 126 |
+
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 127 |
+
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 128 |
+
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
| 129 |
+
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 130 |
+
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 131 |
+
"model.layers.12.self_attn.q_norm.weight": "model.safetensors",
|
| 132 |
+
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 133 |
+
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 134 |
+
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 135 |
+
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 136 |
+
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 137 |
+
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 138 |
+
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 139 |
+
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
| 140 |
+
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 141 |
+
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 142 |
+
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
| 143 |
+
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 144 |
+
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 145 |
+
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
| 146 |
+
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 147 |
+
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 148 |
+
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 149 |
+
"model.layers.13.self_attn.k_norm.weight": "model.safetensors",
|
| 150 |
+
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 151 |
+
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 152 |
+
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 153 |
+
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
| 154 |
+
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 155 |
+
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 156 |
+
"model.layers.13.self_attn.q_norm.weight": "model.safetensors",
|
| 157 |
+
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 158 |
+
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 159 |
+
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 160 |
+
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 161 |
+
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 162 |
+
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 163 |
+
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 164 |
+
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
| 165 |
+
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 166 |
+
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 167 |
+
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
| 168 |
+
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 169 |
+
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 170 |
+
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
| 171 |
+
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 172 |
+
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 173 |
+
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 174 |
+
"model.layers.14.self_attn.k_norm.weight": "model.safetensors",
|
| 175 |
+
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 176 |
+
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 177 |
+
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 178 |
+
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
| 179 |
+
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 180 |
+
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 181 |
+
"model.layers.14.self_attn.q_norm.weight": "model.safetensors",
|
| 182 |
+
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 183 |
+
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 184 |
+
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 185 |
+
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 186 |
+
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 187 |
+
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 188 |
+
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 189 |
+
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
| 190 |
+
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 191 |
+
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 192 |
+
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
| 193 |
+
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 194 |
+
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 195 |
+
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
| 196 |
+
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 197 |
+
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 198 |
+
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 199 |
+
"model.layers.15.self_attn.k_norm.weight": "model.safetensors",
|
| 200 |
+
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 201 |
+
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 202 |
+
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 203 |
+
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
| 204 |
+
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 205 |
+
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 206 |
+
"model.layers.15.self_attn.q_norm.weight": "model.safetensors",
|
| 207 |
+
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 208 |
+
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 209 |
+
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 210 |
+
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 211 |
+
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 212 |
+
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 213 |
+
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 214 |
+
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
| 215 |
+
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 216 |
+
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 217 |
+
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
| 218 |
+
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 219 |
+
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 220 |
+
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
| 221 |
+
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 222 |
+
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 223 |
+
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 224 |
+
"model.layers.16.self_attn.k_norm.weight": "model.safetensors",
|
| 225 |
+
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 226 |
+
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 227 |
+
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 228 |
+
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
| 229 |
+
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 230 |
+
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 231 |
+
"model.layers.16.self_attn.q_norm.weight": "model.safetensors",
|
| 232 |
+
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 233 |
+
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 234 |
+
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 235 |
+
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 236 |
+
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 237 |
+
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 238 |
+
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 239 |
+
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
| 240 |
+
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 241 |
+
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 242 |
+
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
| 243 |
+
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 244 |
+
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 245 |
+
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
| 246 |
+
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 247 |
+
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 248 |
+
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 249 |
+
"model.layers.17.self_attn.k_norm.weight": "model.safetensors",
|
| 250 |
+
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 251 |
+
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 252 |
+
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 253 |
+
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
| 254 |
+
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 255 |
+
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 256 |
+
"model.layers.17.self_attn.q_norm.weight": "model.safetensors",
|
| 257 |
+
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 258 |
+
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 259 |
+
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 260 |
+
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 261 |
+
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 262 |
+
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 263 |
+
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 264 |
+
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
| 265 |
+
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 266 |
+
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 267 |
+
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
| 268 |
+
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 269 |
+
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 270 |
+
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
| 271 |
+
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 272 |
+
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 273 |
+
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 274 |
+
"model.layers.18.self_attn.k_norm.weight": "model.safetensors",
|
| 275 |
+
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 276 |
+
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 277 |
+
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 278 |
+
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
| 279 |
+
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 280 |
+
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 281 |
+
"model.layers.18.self_attn.q_norm.weight": "model.safetensors",
|
| 282 |
+
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 283 |
+
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 284 |
+
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 285 |
+
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 286 |
+
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 287 |
+
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 288 |
+
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 289 |
+
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
| 290 |
+
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 291 |
+
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 292 |
+
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
| 293 |
+
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 294 |
+
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 295 |
+
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
| 296 |
+
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 297 |
+
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 298 |
+
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 299 |
+
"model.layers.19.self_attn.k_norm.weight": "model.safetensors",
|
| 300 |
+
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 301 |
+
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 302 |
+
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 303 |
+
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
| 304 |
+
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 305 |
+
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 306 |
+
"model.layers.19.self_attn.q_norm.weight": "model.safetensors",
|
| 307 |
+
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 308 |
+
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 309 |
+
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 310 |
+
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 311 |
+
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 312 |
+
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 313 |
+
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 314 |
+
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
| 315 |
+
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 316 |
+
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 317 |
+
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
| 318 |
+
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 319 |
+
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 320 |
+
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
| 321 |
+
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 322 |
+
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 323 |
+
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 324 |
+
"model.layers.2.self_attn.k_norm.weight": "model.safetensors",
|
| 325 |
+
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 326 |
+
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 327 |
+
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 328 |
+
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 329 |
+
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 330 |
+
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 331 |
+
"model.layers.2.self_attn.q_norm.weight": "model.safetensors",
|
| 332 |
+
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 333 |
+
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 334 |
+
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 335 |
+
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 336 |
+
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 337 |
+
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 338 |
+
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 339 |
+
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 340 |
+
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 341 |
+
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 342 |
+
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 343 |
+
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 344 |
+
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 345 |
+
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 346 |
+
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 347 |
+
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 348 |
+
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 349 |
+
"model.layers.20.self_attn.k_norm.weight": "model.safetensors",
|
| 350 |
+
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 351 |
+
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 352 |
+
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 353 |
+
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 354 |
+
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 355 |
+
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 356 |
+
"model.layers.20.self_attn.q_norm.weight": "model.safetensors",
|
| 357 |
+
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 358 |
+
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 359 |
+
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 360 |
+
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 361 |
+
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 362 |
+
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 363 |
+
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 364 |
+
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 365 |
+
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 366 |
+
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 367 |
+
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 368 |
+
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 369 |
+
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 370 |
+
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 371 |
+
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 372 |
+
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 373 |
+
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 374 |
+
"model.layers.21.self_attn.k_norm.weight": "model.safetensors",
|
| 375 |
+
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 376 |
+
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 377 |
+
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 378 |
+
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 379 |
+
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 380 |
+
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 381 |
+
"model.layers.21.self_attn.q_norm.weight": "model.safetensors",
|
| 382 |
+
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 383 |
+
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 384 |
+
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 385 |
+
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 386 |
+
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 387 |
+
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 388 |
+
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 389 |
+
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 390 |
+
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 391 |
+
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 392 |
+
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 393 |
+
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 394 |
+
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 395 |
+
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 396 |
+
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 397 |
+
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 398 |
+
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 399 |
+
"model.layers.22.self_attn.k_norm.weight": "model.safetensors",
|
| 400 |
+
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 401 |
+
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 402 |
+
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 403 |
+
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 404 |
+
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 405 |
+
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 406 |
+
"model.layers.22.self_attn.q_norm.weight": "model.safetensors",
|
| 407 |
+
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 408 |
+
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 409 |
+
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 410 |
+
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 411 |
+
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 412 |
+
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 413 |
+
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 414 |
+
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 415 |
+
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 416 |
+
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 417 |
+
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 418 |
+
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 419 |
+
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 420 |
+
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 421 |
+
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 422 |
+
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 423 |
+
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 424 |
+
"model.layers.23.self_attn.k_norm.weight": "model.safetensors",
|
| 425 |
+
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 426 |
+
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 427 |
+
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 428 |
+
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 429 |
+
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 430 |
+
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 431 |
+
"model.layers.23.self_attn.q_norm.weight": "model.safetensors",
|
| 432 |
+
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 433 |
+
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 434 |
+
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 435 |
+
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 436 |
+
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 437 |
+
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 438 |
+
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 439 |
+
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 440 |
+
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 441 |
+
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 442 |
+
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 443 |
+
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 444 |
+
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 445 |
+
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 446 |
+
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 447 |
+
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 448 |
+
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 449 |
+
"model.layers.24.self_attn.k_norm.weight": "model.safetensors",
|
| 450 |
+
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 451 |
+
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 452 |
+
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 453 |
+
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 454 |
+
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 455 |
+
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 456 |
+
"model.layers.24.self_attn.q_norm.weight": "model.safetensors",
|
| 457 |
+
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 458 |
+
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 459 |
+
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 460 |
+
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 461 |
+
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 462 |
+
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 463 |
+
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 464 |
+
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 465 |
+
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 466 |
+
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 467 |
+
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 468 |
+
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 469 |
+
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 470 |
+
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 471 |
+
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 472 |
+
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 473 |
+
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 474 |
+
"model.layers.25.self_attn.k_norm.weight": "model.safetensors",
|
| 475 |
+
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 476 |
+
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 477 |
+
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 478 |
+
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 479 |
+
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 480 |
+
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 481 |
+
"model.layers.25.self_attn.q_norm.weight": "model.safetensors",
|
| 482 |
+
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 483 |
+
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 484 |
+
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 485 |
+
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 486 |
+
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 487 |
+
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 488 |
+
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 489 |
+
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 490 |
+
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 491 |
+
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 492 |
+
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 493 |
+
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 494 |
+
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 495 |
+
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 496 |
+
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 497 |
+
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 498 |
+
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 499 |
+
"model.layers.26.self_attn.k_norm.weight": "model.safetensors",
|
| 500 |
+
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 501 |
+
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 502 |
+
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 503 |
+
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 504 |
+
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 505 |
+
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 506 |
+
"model.layers.26.self_attn.q_norm.weight": "model.safetensors",
|
| 507 |
+
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 508 |
+
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 509 |
+
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 510 |
+
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 511 |
+
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 512 |
+
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 513 |
+
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 514 |
+
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 515 |
+
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 516 |
+
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 517 |
+
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 518 |
+
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 519 |
+
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 520 |
+
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 521 |
+
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 522 |
+
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 523 |
+
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 524 |
+
"model.layers.27.self_attn.k_norm.weight": "model.safetensors",
|
| 525 |
+
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 526 |
+
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 527 |
+
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 528 |
+
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 529 |
+
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 530 |
+
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 531 |
+
"model.layers.27.self_attn.q_norm.weight": "model.safetensors",
|
| 532 |
+
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 533 |
+
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 534 |
+
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 535 |
+
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 536 |
+
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 537 |
+
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 538 |
+
"model.layers.28.input_layernorm.weight": "model.safetensors",
|
| 539 |
+
"model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
| 540 |
+
"model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
| 541 |
+
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
| 542 |
+
"model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
| 543 |
+
"model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
| 544 |
+
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
| 545 |
+
"model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
| 546 |
+
"model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
| 547 |
+
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
| 548 |
+
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
| 549 |
+
"model.layers.28.self_attn.k_norm.weight": "model.safetensors",
|
| 550 |
+
"model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
| 551 |
+
"model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
| 552 |
+
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
| 553 |
+
"model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
| 554 |
+
"model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
| 555 |
+
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
| 556 |
+
"model.layers.28.self_attn.q_norm.weight": "model.safetensors",
|
| 557 |
+
"model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
| 558 |
+
"model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
| 559 |
+
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
| 560 |
+
"model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
| 561 |
+
"model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
| 562 |
+
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
| 563 |
+
"model.layers.29.input_layernorm.weight": "model.safetensors",
|
| 564 |
+
"model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
| 565 |
+
"model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
| 566 |
+
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
| 567 |
+
"model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
| 568 |
+
"model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
| 569 |
+
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
| 570 |
+
"model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
| 571 |
+
"model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
| 572 |
+
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
| 573 |
+
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
| 574 |
+
"model.layers.29.self_attn.k_norm.weight": "model.safetensors",
|
| 575 |
+
"model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
| 576 |
+
"model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
| 577 |
+
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
| 578 |
+
"model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
| 579 |
+
"model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
| 580 |
+
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
| 581 |
+
"model.layers.29.self_attn.q_norm.weight": "model.safetensors",
|
| 582 |
+
"model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
| 583 |
+
"model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
| 584 |
+
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
| 585 |
+
"model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
| 586 |
+
"model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
| 587 |
+
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
| 588 |
+
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 589 |
+
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 590 |
+
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 591 |
+
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 592 |
+
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 593 |
+
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 594 |
+
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 595 |
+
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 596 |
+
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 597 |
+
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 598 |
+
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 599 |
+
"model.layers.3.self_attn.k_norm.weight": "model.safetensors",
|
| 600 |
+
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 601 |
+
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 602 |
+
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 603 |
+
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 604 |
+
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 605 |
+
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 606 |
+
"model.layers.3.self_attn.q_norm.weight": "model.safetensors",
|
| 607 |
+
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 608 |
+
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 609 |
+
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 610 |
+
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 611 |
+
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 612 |
+
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 613 |
+
"model.layers.30.input_layernorm.weight": "model.safetensors",
|
| 614 |
+
"model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
| 615 |
+
"model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
| 616 |
+
"model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
| 617 |
+
"model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
| 618 |
+
"model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
| 619 |
+
"model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
| 620 |
+
"model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
| 621 |
+
"model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
| 622 |
+
"model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
| 623 |
+
"model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
| 624 |
+
"model.layers.30.self_attn.k_norm.weight": "model.safetensors",
|
| 625 |
+
"model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
| 626 |
+
"model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
| 627 |
+
"model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
| 628 |
+
"model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
| 629 |
+
"model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
| 630 |
+
"model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
| 631 |
+
"model.layers.30.self_attn.q_norm.weight": "model.safetensors",
|
| 632 |
+
"model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
| 633 |
+
"model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
| 634 |
+
"model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
| 635 |
+
"model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
| 636 |
+
"model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
| 637 |
+
"model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
| 638 |
+
"model.layers.31.input_layernorm.weight": "model.safetensors",
|
| 639 |
+
"model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
| 640 |
+
"model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
| 641 |
+
"model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
| 642 |
+
"model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
| 643 |
+
"model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
| 644 |
+
"model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
| 645 |
+
"model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
| 646 |
+
"model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
| 647 |
+
"model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
| 648 |
+
"model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
| 649 |
+
"model.layers.31.self_attn.k_norm.weight": "model.safetensors",
|
| 650 |
+
"model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
| 651 |
+
"model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
| 652 |
+
"model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
| 653 |
+
"model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
| 654 |
+
"model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
| 655 |
+
"model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
| 656 |
+
"model.layers.31.self_attn.q_norm.weight": "model.safetensors",
|
| 657 |
+
"model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
| 658 |
+
"model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
| 659 |
+
"model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
| 660 |
+
"model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
| 661 |
+
"model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
| 662 |
+
"model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
| 663 |
+
"model.layers.32.input_layernorm.weight": "model.safetensors",
|
| 664 |
+
"model.layers.32.mlp.down_proj.biases": "model.safetensors",
|
| 665 |
+
"model.layers.32.mlp.down_proj.scales": "model.safetensors",
|
| 666 |
+
"model.layers.32.mlp.down_proj.weight": "model.safetensors",
|
| 667 |
+
"model.layers.32.mlp.gate_proj.biases": "model.safetensors",
|
| 668 |
+
"model.layers.32.mlp.gate_proj.scales": "model.safetensors",
|
| 669 |
+
"model.layers.32.mlp.gate_proj.weight": "model.safetensors",
|
| 670 |
+
"model.layers.32.mlp.up_proj.biases": "model.safetensors",
|
| 671 |
+
"model.layers.32.mlp.up_proj.scales": "model.safetensors",
|
| 672 |
+
"model.layers.32.mlp.up_proj.weight": "model.safetensors",
|
| 673 |
+
"model.layers.32.post_attention_layernorm.weight": "model.safetensors",
|
| 674 |
+
"model.layers.32.self_attn.k_norm.weight": "model.safetensors",
|
| 675 |
+
"model.layers.32.self_attn.k_proj.biases": "model.safetensors",
|
| 676 |
+
"model.layers.32.self_attn.k_proj.scales": "model.safetensors",
|
| 677 |
+
"model.layers.32.self_attn.k_proj.weight": "model.safetensors",
|
| 678 |
+
"model.layers.32.self_attn.o_proj.biases": "model.safetensors",
|
| 679 |
+
"model.layers.32.self_attn.o_proj.scales": "model.safetensors",
|
| 680 |
+
"model.layers.32.self_attn.o_proj.weight": "model.safetensors",
|
| 681 |
+
"model.layers.32.self_attn.q_norm.weight": "model.safetensors",
|
| 682 |
+
"model.layers.32.self_attn.q_proj.biases": "model.safetensors",
|
| 683 |
+
"model.layers.32.self_attn.q_proj.scales": "model.safetensors",
|
| 684 |
+
"model.layers.32.self_attn.q_proj.weight": "model.safetensors",
|
| 685 |
+
"model.layers.32.self_attn.v_proj.biases": "model.safetensors",
|
| 686 |
+
"model.layers.32.self_attn.v_proj.scales": "model.safetensors",
|
| 687 |
+
"model.layers.32.self_attn.v_proj.weight": "model.safetensors",
|
| 688 |
+
"model.layers.33.input_layernorm.weight": "model.safetensors",
|
| 689 |
+
"model.layers.33.mlp.down_proj.biases": "model.safetensors",
|
| 690 |
+
"model.layers.33.mlp.down_proj.scales": "model.safetensors",
|
| 691 |
+
"model.layers.33.mlp.down_proj.weight": "model.safetensors",
|
| 692 |
+
"model.layers.33.mlp.gate_proj.biases": "model.safetensors",
|
| 693 |
+
"model.layers.33.mlp.gate_proj.scales": "model.safetensors",
|
| 694 |
+
"model.layers.33.mlp.gate_proj.weight": "model.safetensors",
|
| 695 |
+
"model.layers.33.mlp.up_proj.biases": "model.safetensors",
|
| 696 |
+
"model.layers.33.mlp.up_proj.scales": "model.safetensors",
|
| 697 |
+
"model.layers.33.mlp.up_proj.weight": "model.safetensors",
|
| 698 |
+
"model.layers.33.post_attention_layernorm.weight": "model.safetensors",
|
| 699 |
+
"model.layers.33.self_attn.k_norm.weight": "model.safetensors",
|
| 700 |
+
"model.layers.33.self_attn.k_proj.biases": "model.safetensors",
|
| 701 |
+
"model.layers.33.self_attn.k_proj.scales": "model.safetensors",
|
| 702 |
+
"model.layers.33.self_attn.k_proj.weight": "model.safetensors",
|
| 703 |
+
"model.layers.33.self_attn.o_proj.biases": "model.safetensors",
|
| 704 |
+
"model.layers.33.self_attn.o_proj.scales": "model.safetensors",
|
| 705 |
+
"model.layers.33.self_attn.o_proj.weight": "model.safetensors",
|
| 706 |
+
"model.layers.33.self_attn.q_norm.weight": "model.safetensors",
|
| 707 |
+
"model.layers.33.self_attn.q_proj.biases": "model.safetensors",
|
| 708 |
+
"model.layers.33.self_attn.q_proj.scales": "model.safetensors",
|
| 709 |
+
"model.layers.33.self_attn.q_proj.weight": "model.safetensors",
|
| 710 |
+
"model.layers.33.self_attn.v_proj.biases": "model.safetensors",
|
| 711 |
+
"model.layers.33.self_attn.v_proj.scales": "model.safetensors",
|
| 712 |
+
"model.layers.33.self_attn.v_proj.weight": "model.safetensors",
|
| 713 |
+
"model.layers.34.input_layernorm.weight": "model.safetensors",
|
| 714 |
+
"model.layers.34.mlp.down_proj.biases": "model.safetensors",
|
| 715 |
+
"model.layers.34.mlp.down_proj.scales": "model.safetensors",
|
| 716 |
+
"model.layers.34.mlp.down_proj.weight": "model.safetensors",
|
| 717 |
+
"model.layers.34.mlp.gate_proj.biases": "model.safetensors",
|
| 718 |
+
"model.layers.34.mlp.gate_proj.scales": "model.safetensors",
|
| 719 |
+
"model.layers.34.mlp.gate_proj.weight": "model.safetensors",
|
| 720 |
+
"model.layers.34.mlp.up_proj.biases": "model.safetensors",
|
| 721 |
+
"model.layers.34.mlp.up_proj.scales": "model.safetensors",
|
| 722 |
+
"model.layers.34.mlp.up_proj.weight": "model.safetensors",
|
| 723 |
+
"model.layers.34.post_attention_layernorm.weight": "model.safetensors",
|
| 724 |
+
"model.layers.34.self_attn.k_norm.weight": "model.safetensors",
|
| 725 |
+
"model.layers.34.self_attn.k_proj.biases": "model.safetensors",
|
| 726 |
+
"model.layers.34.self_attn.k_proj.scales": "model.safetensors",
|
| 727 |
+
"model.layers.34.self_attn.k_proj.weight": "model.safetensors",
|
| 728 |
+
"model.layers.34.self_attn.o_proj.biases": "model.safetensors",
|
| 729 |
+
"model.layers.34.self_attn.o_proj.scales": "model.safetensors",
|
| 730 |
+
"model.layers.34.self_attn.o_proj.weight": "model.safetensors",
|
| 731 |
+
"model.layers.34.self_attn.q_norm.weight": "model.safetensors",
|
| 732 |
+
"model.layers.34.self_attn.q_proj.biases": "model.safetensors",
|
| 733 |
+
"model.layers.34.self_attn.q_proj.scales": "model.safetensors",
|
| 734 |
+
"model.layers.34.self_attn.q_proj.weight": "model.safetensors",
|
| 735 |
+
"model.layers.34.self_attn.v_proj.biases": "model.safetensors",
|
| 736 |
+
"model.layers.34.self_attn.v_proj.scales": "model.safetensors",
|
| 737 |
+
"model.layers.34.self_attn.v_proj.weight": "model.safetensors",
|
| 738 |
+
"model.layers.35.input_layernorm.weight": "model.safetensors",
|
| 739 |
+
"model.layers.35.mlp.down_proj.biases": "model.safetensors",
|
| 740 |
+
"model.layers.35.mlp.down_proj.scales": "model.safetensors",
|
| 741 |
+
"model.layers.35.mlp.down_proj.weight": "model.safetensors",
|
| 742 |
+
"model.layers.35.mlp.gate_proj.biases": "model.safetensors",
|
| 743 |
+
"model.layers.35.mlp.gate_proj.scales": "model.safetensors",
|
| 744 |
+
"model.layers.35.mlp.gate_proj.weight": "model.safetensors",
|
| 745 |
+
"model.layers.35.mlp.up_proj.biases": "model.safetensors",
|
| 746 |
+
"model.layers.35.mlp.up_proj.scales": "model.safetensors",
|
| 747 |
+
"model.layers.35.mlp.up_proj.weight": "model.safetensors",
|
| 748 |
+
"model.layers.35.post_attention_layernorm.weight": "model.safetensors",
|
| 749 |
+
"model.layers.35.self_attn.k_norm.weight": "model.safetensors",
|
| 750 |
+
"model.layers.35.self_attn.k_proj.biases": "model.safetensors",
|
| 751 |
+
"model.layers.35.self_attn.k_proj.scales": "model.safetensors",
|
| 752 |
+
"model.layers.35.self_attn.k_proj.weight": "model.safetensors",
|
| 753 |
+
"model.layers.35.self_attn.o_proj.biases": "model.safetensors",
|
| 754 |
+
"model.layers.35.self_attn.o_proj.scales": "model.safetensors",
|
| 755 |
+
"model.layers.35.self_attn.o_proj.weight": "model.safetensors",
|
| 756 |
+
"model.layers.35.self_attn.q_norm.weight": "model.safetensors",
|
| 757 |
+
"model.layers.35.self_attn.q_proj.biases": "model.safetensors",
|
| 758 |
+
"model.layers.35.self_attn.q_proj.scales": "model.safetensors",
|
| 759 |
+
"model.layers.35.self_attn.q_proj.weight": "model.safetensors",
|
| 760 |
+
"model.layers.35.self_attn.v_proj.biases": "model.safetensors",
|
| 761 |
+
"model.layers.35.self_attn.v_proj.scales": "model.safetensors",
|
| 762 |
+
"model.layers.35.self_attn.v_proj.weight": "model.safetensors",
|
| 763 |
+
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 764 |
+
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 765 |
+
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 766 |
+
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 767 |
+
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 768 |
+
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 769 |
+
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 770 |
+
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 771 |
+
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 772 |
+
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 773 |
+
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 774 |
+
"model.layers.4.self_attn.k_norm.weight": "model.safetensors",
|
| 775 |
+
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 776 |
+
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 777 |
+
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 778 |
+
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 779 |
+
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 780 |
+
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 781 |
+
"model.layers.4.self_attn.q_norm.weight": "model.safetensors",
|
| 782 |
+
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 783 |
+
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 784 |
+
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 785 |
+
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 786 |
+
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 787 |
+
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 788 |
+
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 789 |
+
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 790 |
+
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 791 |
+
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 792 |
+
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 793 |
+
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 794 |
+
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 795 |
+
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 796 |
+
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 797 |
+
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 798 |
+
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 799 |
+
"model.layers.5.self_attn.k_norm.weight": "model.safetensors",
|
| 800 |
+
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 801 |
+
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 802 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 803 |
+
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 804 |
+
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 805 |
+
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 806 |
+
"model.layers.5.self_attn.q_norm.weight": "model.safetensors",
|
| 807 |
+
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 808 |
+
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 809 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 810 |
+
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 811 |
+
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 812 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 813 |
+
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 814 |
+
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 815 |
+
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 816 |
+
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 817 |
+
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 818 |
+
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 819 |
+
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 820 |
+
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 821 |
+
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 822 |
+
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 823 |
+
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 824 |
+
"model.layers.6.self_attn.k_norm.weight": "model.safetensors",
|
| 825 |
+
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 826 |
+
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 827 |
+
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 828 |
+
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 829 |
+
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 830 |
+
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 831 |
+
"model.layers.6.self_attn.q_norm.weight": "model.safetensors",
|
| 832 |
+
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 833 |
+
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 834 |
+
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 835 |
+
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 836 |
+
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 837 |
+
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 838 |
+
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 839 |
+
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 840 |
+
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 841 |
+
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 842 |
+
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 843 |
+
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 844 |
+
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 845 |
+
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 846 |
+
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 847 |
+
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 848 |
+
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 849 |
+
"model.layers.7.self_attn.k_norm.weight": "model.safetensors",
|
| 850 |
+
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 851 |
+
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 852 |
+
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 853 |
+
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 854 |
+
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 855 |
+
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 856 |
+
"model.layers.7.self_attn.q_norm.weight": "model.safetensors",
|
| 857 |
+
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 858 |
+
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 859 |
+
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 860 |
+
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 861 |
+
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 862 |
+
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 863 |
+
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 864 |
+
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 865 |
+
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 866 |
+
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 867 |
+
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 868 |
+
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 869 |
+
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 870 |
+
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 871 |
+
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 872 |
+
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 873 |
+
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 874 |
+
"model.layers.8.self_attn.k_norm.weight": "model.safetensors",
|
| 875 |
+
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 876 |
+
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 877 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 878 |
+
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 879 |
+
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 880 |
+
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 881 |
+
"model.layers.8.self_attn.q_norm.weight": "model.safetensors",
|
| 882 |
+
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 883 |
+
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 884 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 885 |
+
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 886 |
+
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 887 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 888 |
+
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 889 |
+
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 890 |
+
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 891 |
+
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 892 |
+
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 893 |
+
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 894 |
+
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 895 |
+
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 896 |
+
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 897 |
+
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 898 |
+
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 899 |
+
"model.layers.9.self_attn.k_norm.weight": "model.safetensors",
|
| 900 |
+
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 901 |
+
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 902 |
+
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 903 |
+
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 904 |
+
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 905 |
+
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 906 |
+
"model.layers.9.self_attn.q_norm.weight": "model.safetensors",
|
| 907 |
+
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 908 |
+
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 909 |
+
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 910 |
+
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 911 |
+
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 912 |
+
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 913 |
+
"model.norm.weight": "model.safetensors"
|
| 914 |
+
}
|
| 915 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 13,
|
| 8 |
+
"content": "<|endoftext|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 14,
|
| 17 |
+
"content": "<|im_start|>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 15,
|
| 26 |
+
"content": "<|im_end|>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"normalizer": {
|
| 35 |
+
"type": "NFC"
|
| 36 |
+
},
|
| 37 |
+
"pre_tokenizer": {
|
| 38 |
+
"type": "Sequence",
|
| 39 |
+
"pretokenizers": [
|
| 40 |
+
{
|
| 41 |
+
"type": "Split",
|
| 42 |
+
"pattern": {
|
| 43 |
+
"Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
|
| 44 |
+
},
|
| 45 |
+
"behavior": "Isolated",
|
| 46 |
+
"invert": false
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"type": "ByteLevel",
|
| 50 |
+
"add_prefix_space": false,
|
| 51 |
+
"trim_offsets": true,
|
| 52 |
+
"use_regex": false
|
| 53 |
+
}
|
| 54 |
+
]
|
| 55 |
+
},
|
| 56 |
+
"post_processor": {
|
| 57 |
+
"type": "ByteLevel",
|
| 58 |
+
"add_prefix_space": false,
|
| 59 |
+
"trim_offsets": false,
|
| 60 |
+
"use_regex": false
|
| 61 |
+
},
|
| 62 |
+
"decoder": {
|
| 63 |
+
"type": "ByteLevel",
|
| 64 |
+
"add_prefix_space": true,
|
| 65 |
+
"trim_offsets": true,
|
| 66 |
+
"use_regex": true
|
| 67 |
+
},
|
| 68 |
+
"model": {
|
| 69 |
+
"type": "BPE",
|
| 70 |
+
"dropout": null,
|
| 71 |
+
"unk_token": null,
|
| 72 |
+
"continuing_subword_prefix": "",
|
| 73 |
+
"end_of_word_suffix": "",
|
| 74 |
+
"fuse_unk": false,
|
| 75 |
+
"byte_fallback": false,
|
| 76 |
+
"ignore_merges": false,
|
| 77 |
+
"vocab": {
|
| 78 |
+
"0": 0,
|
| 79 |
+
"1": 1,
|
| 80 |
+
"2": 2,
|
| 81 |
+
"3": 3,
|
| 82 |
+
"4": 4,
|
| 83 |
+
"5": 5,
|
| 84 |
+
"6": 6,
|
| 85 |
+
"7": 7,
|
| 86 |
+
"8": 8,
|
| 87 |
+
"9": 9,
|
| 88 |
+
"Ċ": 10,
|
| 89 |
+
"user": 11,
|
| 90 |
+
"assistant": 12
|
| 91 |
+
},
|
| 92 |
+
"merges": []
|
| 93 |
+
}
|
| 94 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"model_max_length": 262144,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"split_special_tokens": false,
|
| 12 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 13 |
+
"unk_token": null
|
| 14 |
+
}
|