update model
#2
by linzhao-amd - opened
This view is limited to 50 files because it contains too many changes. See the raw diff here.
- README.md +14 -37
- config.json +1 -1538
- model.safetensors-00001-of-00094.safetensors +1 -1
- model.safetensors-00002-of-00094.safetensors +1 -1
- model.safetensors-00003-of-00094.safetensors +1 -1
- model.safetensors-00004-of-00094.safetensors +1 -1
- model.safetensors-00005-of-00094.safetensors +1 -1
- model.safetensors-00006-of-00094.safetensors +1 -1
- model.safetensors-00007-of-00094.safetensors +1 -1
- model.safetensors-00008-of-00094.safetensors +1 -1
- model.safetensors-00009-of-00094.safetensors +1 -1
- model.safetensors-00010-of-00094.safetensors +1 -1
- model.safetensors-00011-of-00094.safetensors +1 -1
- model.safetensors-00012-of-00094.safetensors +1 -1
- model.safetensors-00013-of-00094.safetensors +1 -1
- model.safetensors-00014-of-00094.safetensors +1 -1
- model.safetensors-00015-of-00094.safetensors +1 -1
- model.safetensors-00016-of-00094.safetensors +1 -1
- model.safetensors-00017-of-00094.safetensors +1 -1
- model.safetensors-00018-of-00094.safetensors +1 -1
- model.safetensors-00019-of-00094.safetensors +1 -1
- model.safetensors-00020-of-00094.safetensors +1 -1
- model.safetensors-00021-of-00094.safetensors +1 -1
- model.safetensors-00022-of-00094.safetensors +1 -1
- model.safetensors-00023-of-00094.safetensors +1 -1
- model.safetensors-00024-of-00094.safetensors +1 -1
- model.safetensors-00025-of-00094.safetensors +1 -1
- model.safetensors-00026-of-00094.safetensors +1 -1
- model.safetensors-00027-of-00094.safetensors +1 -1
- model.safetensors-00028-of-00094.safetensors +1 -1
- model.safetensors-00029-of-00094.safetensors +1 -1
- model.safetensors-00030-of-00094.safetensors +1 -1
- model.safetensors-00031-of-00094.safetensors +1 -1
- model.safetensors-00032-of-00094.safetensors +1 -1
- model.safetensors-00033-of-00094.safetensors +1 -1
- model.safetensors-00034-of-00094.safetensors +1 -1
- model.safetensors-00035-of-00094.safetensors +1 -1
- model.safetensors-00036-of-00094.safetensors +1 -1
- model.safetensors-00037-of-00094.safetensors +1 -1
- model.safetensors-00038-of-00094.safetensors +1 -1
- model.safetensors-00039-of-00094.safetensors +1 -1
- model.safetensors-00040-of-00094.safetensors +1 -1
- model.safetensors-00041-of-00094.safetensors +1 -1
- model.safetensors-00042-of-00094.safetensors +1 -1
- model.safetensors-00043-of-00094.safetensors +1 -1
- model.safetensors-00044-of-00094.safetensors +1 -1
- model.safetensors-00045-of-00094.safetensors +1 -1
- model.safetensors-00046-of-00094.safetensors +1 -1
- model.safetensors-00047-of-00094.safetensors +1 -1
- model.safetensors-00048-of-00094.safetensors +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
-
- Qwen/Qwen3.5-397B-A17B
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
library_name: transformers
|
|
@@ -14,13 +14,12 @@ license_link: https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/LICENSE
|
|
| 14 |
- **Input:** Text
|
| 15 |
- **Output:** Text
|
| 16 |
- **Supported Hardware Microarchitecture:** AMD MI300 MI350/MI355
|
| 17 |
-
- **ROCm**: 7.0
|
| 18 |
-
- **PyTorch**: 2.
|
| 19 |
-
- **Transformers**: 5.
|
| 20 |
- **Operating System(s):** Linux
|
| 21 |
- **Inference Engine:** [SGLang](https://docs.sglang.ai/)/[vLLM](https://docs.vllm.ai/en/latest/)
|
| 22 |
-
- **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (v0.11
|
| 23 |
-
- **Quantized layers:** Experts in language model only
|
| 24 |
- **Weight quantization:** OCP MXFP4, Static
|
| 25 |
- **Activation quantization:** OCP MXFP4, Dynamic
|
| 26 |
|
|
@@ -32,35 +31,13 @@ The model was quantized from [Qwen/Qwen3.5-397B-A17B-FP8](https://huggingface.co
|
|
| 32 |
|
| 33 |
**Quantization scripts:**
|
| 34 |
```
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
kv_layers_name=["*k_proj", "*v_proj"],
|
| 43 |
-
q_layer_name="*q_proj"
|
| 44 |
-
)
|
| 45 |
-
LLMTemplate.register_template(qwen3_5_moe_template)
|
| 46 |
-
|
| 47 |
-
# Configuration
|
| 48 |
-
ckpt_path = "Qwen/Qwen3.5-397B-A17B-FP8"
|
| 49 |
-
output_dir = "amd/Qwen3.5-397B-A17B-MXFP4"
|
| 50 |
-
quant_scheme = "mxfp4"
|
| 51 |
-
exclude_layers = ["lm_head", "model.visual.*", "mtp.*", "*mlp.gate", "*shared_expert_gate*", "*.linear_attn.*", "*.self_attn.*", "*.shared_expert.*"]
|
| 52 |
-
|
| 53 |
-
# Get quant config from template
|
| 54 |
-
template = LLMTemplate.get("qwen3_5_moe")
|
| 55 |
-
quant_config = template.get_config(scheme=quant_scheme, exclude_layers=exclude_layers)
|
| 56 |
-
|
| 57 |
-
# Quantize with File-to-file mode
|
| 58 |
-
profiler = GlobalProfiler(output_path=os.path.join(output_dir, "quark_profile.yaml"))
|
| 59 |
-
quantizer = ModelQuantizer(quant_config)
|
| 60 |
-
quantizer.direct_quantize_checkpoint(
|
| 61 |
-
pretrained_model_path=ckpt_path,
|
| 62 |
-
save_path=output_dir,
|
| 63 |
-
)
|
| 64 |
```
|
| 65 |
For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.
|
| 66 |
|
|
@@ -95,13 +72,13 @@ The model was evaluated on gsm8k benchmarks using the [vllm](https://github.com/
|
|
| 95 |
|
| 96 |
### Reproduction
|
| 97 |
|
| 98 |
-
The GSM8K results were obtained using the vLLM framework, based on the Docker image `rocm/vllm-dev:nightly_main_20260211`, and vLLM is installed inside the container.
|
| 99 |
|
| 100 |
#### Evaluating model in a new terminal
|
| 101 |
```
|
| 102 |
lm_eval \
|
| 103 |
--model vllm \
|
| 104 |
-
--model_args pretrained=$MODEL,tensor_parallel_size=
|
| 105 |
--tasks gsm8k --num_fewshot 5 \
|
| 106 |
--batch_size auto
|
| 107 |
```
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
+
- Qwen/Qwen3.5-397B-A17B
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
library_name: transformers
|
|
|
|
| 14 |
- **Input:** Text
|
| 15 |
- **Output:** Text
|
| 16 |
- **Supported Hardware Microarchitecture:** AMD MI300 MI350/MI355
|
| 17 |
+
- **ROCm**: 7.0
|
| 18 |
+
- **PyTorch**: 2.8.0
|
| 19 |
+
- **Transformers**: 5.2.0
|
| 20 |
- **Operating System(s):** Linux
|
| 21 |
- **Inference Engine:** [SGLang](https://docs.sglang.ai/)/[vLLM](https://docs.vllm.ai/en/latest/)
|
| 22 |
+
- **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (v0.11)
|
|
|
|
| 23 |
- **Weight quantization:** OCP MXFP4, Static
|
| 24 |
- **Activation quantization:** OCP MXFP4, Dynamic
|
| 25 |
|
|
|
|
| 31 |
|
| 32 |
**Quantization scripts:**
|
| 33 |
```
|
| 34 |
+
cd Quark/examples/torch/language_modeling/llm_ptq/
|
| 35 |
+
export exclude_layers="lm_head model.visual.* mtp.* *mlp.gate *shared_expert_gate* *.linear_attn.* *.self_attn.* *.shared_expert.*"
|
| 36 |
+
python3 quantize_quark.py --model_dir $MODEL_DIR \
|
| 37 |
+
--quant_scheme mxfp4 \
|
| 38 |
+
--file2file_quantization \
|
| 39 |
+
--exclude_layers $exclude_layers \
|
| 40 |
+
--output_dir $output_dir \
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
```
|
| 42 |
For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.
|
| 43 |
|
|
|
|
| 72 |
|
| 73 |
### Reproduction
|
| 74 |
|
| 75 |
+
The GSM8K results were obtained using the vLLM framework, based on the Docker image `rocm/vllm-dev:nightly_main_20260211`, and vLLM is installed inside the container with fixes applied for model support.
|
| 76 |
|
| 77 |
#### Evaluating model in a new terminal
|
| 78 |
```
|
| 79 |
lm_eval \
|
| 80 |
--model vllm \
|
| 81 |
+
--model_args pretrained=$MODEL,tensor_parallel_size=1,max_model_len=262144,gpu_memory_utilization=0.90,max_gen_toks=2048,trust_remote_code=True,reasoning_parser=qwen3 \
|
| 82 |
--tasks gsm8k --num_fewshot 5 \
|
| 83 |
--batch_size auto
|
| 84 |
```
|
config.json
CHANGED
|
@@ -964,1543 +964,6 @@
|
|
| 964 |
"model.visual.blocks.9.norm2",
|
| 965 |
"model.visual.merger.linear_fc1",
|
| 966 |
"model.visual.merger.linear_fc2",
|
| 967 |
-
"mtp.fc",
|
| 968 |
-
"mtp.layers.0.mlp.experts.0.down_proj",
|
| 969 |
-
"mtp.layers.0.mlp.experts.0.gate_proj",
|
| 970 |
-
"mtp.layers.0.mlp.experts.0.up_proj",
|
| 971 |
-
"mtp.layers.0.mlp.experts.1.down_proj",
|
| 972 |
-
"mtp.layers.0.mlp.experts.1.gate_proj",
|
| 973 |
-
"mtp.layers.0.mlp.experts.1.up_proj",
|
| 974 |
-
"mtp.layers.0.mlp.experts.10.down_proj",
|
| 975 |
-
"mtp.layers.0.mlp.experts.10.gate_proj",
|
| 976 |
-
"mtp.layers.0.mlp.experts.10.up_proj",
|
| 977 |
-
"mtp.layers.0.mlp.experts.100.down_proj",
|
| 978 |
-
"mtp.layers.0.mlp.experts.100.gate_proj",
|
| 979 |
-
"mtp.layers.0.mlp.experts.100.up_proj",
|
| 980 |
-
"mtp.layers.0.mlp.experts.101.down_proj",
|
| 981 |
-
"mtp.layers.0.mlp.experts.101.gate_proj",
|
| 982 |
-
"mtp.layers.0.mlp.experts.101.up_proj",
|
| 983 |
-
"mtp.layers.0.mlp.experts.102.down_proj",
|
| 984 |
-
"mtp.layers.0.mlp.experts.102.gate_proj",
|
| 985 |
-
"mtp.layers.0.mlp.experts.102.up_proj",
|
| 986 |
-
"mtp.layers.0.mlp.experts.103.down_proj",
|
| 987 |
-
"mtp.layers.0.mlp.experts.103.gate_proj",
|
| 988 |
-
"mtp.layers.0.mlp.experts.103.up_proj",
|
| 989 |
-
"mtp.layers.0.mlp.experts.104.down_proj",
|
| 990 |
-
"mtp.layers.0.mlp.experts.104.gate_proj",
|
| 991 |
-
"mtp.layers.0.mlp.experts.104.up_proj",
|
| 992 |
-
"mtp.layers.0.mlp.experts.105.down_proj",
|
| 993 |
-
"mtp.layers.0.mlp.experts.105.gate_proj",
|
| 994 |
-
"mtp.layers.0.mlp.experts.105.up_proj",
|
| 995 |
-
"mtp.layers.0.mlp.experts.106.down_proj",
|
| 996 |
-
"mtp.layers.0.mlp.experts.106.gate_proj",
|
| 997 |
-
"mtp.layers.0.mlp.experts.106.up_proj",
|
| 998 |
-
"mtp.layers.0.mlp.experts.107.down_proj",
|
| 999 |
-
"mtp.layers.0.mlp.experts.107.gate_proj",
|
| 1000 |
-
"mtp.layers.0.mlp.experts.107.up_proj",
|
| 1001 |
-
"mtp.layers.0.mlp.experts.108.down_proj",
|
| 1002 |
-
"mtp.layers.0.mlp.experts.108.gate_proj",
|
| 1003 |
-
"mtp.layers.0.mlp.experts.108.up_proj",
|
| 1004 |
-
"mtp.layers.0.mlp.experts.109.down_proj",
|
| 1005 |
-
"mtp.layers.0.mlp.experts.109.gate_proj",
|
| 1006 |
-
"mtp.layers.0.mlp.experts.109.up_proj",
|
| 1007 |
-
"mtp.layers.0.mlp.experts.11.down_proj",
|
| 1008 |
-
"mtp.layers.0.mlp.experts.11.gate_proj",
|
| 1009 |
-
"mtp.layers.0.mlp.experts.11.up_proj",
|
| 1010 |
-
"mtp.layers.0.mlp.experts.110.down_proj",
|
| 1011 |
-
"mtp.layers.0.mlp.experts.110.gate_proj",
|
| 1012 |
-
"mtp.layers.0.mlp.experts.110.up_proj",
|
| 1013 |
-
"mtp.layers.0.mlp.experts.111.down_proj",
|
| 1014 |
-
"mtp.layers.0.mlp.experts.111.gate_proj",
|
| 1015 |
-
"mtp.layers.0.mlp.experts.111.up_proj",
|
| 1016 |
-
"mtp.layers.0.mlp.experts.112.down_proj",
|
| 1017 |
-
"mtp.layers.0.mlp.experts.112.gate_proj",
|
| 1018 |
-
"mtp.layers.0.mlp.experts.112.up_proj",
|
| 1019 |
-
"mtp.layers.0.mlp.experts.113.down_proj",
|
| 1020 |
-
"mtp.layers.0.mlp.experts.113.gate_proj",
|
| 1021 |
-
"mtp.layers.0.mlp.experts.113.up_proj",
|
| 1022 |
-
"mtp.layers.0.mlp.experts.114.down_proj",
|
| 1023 |
-
"mtp.layers.0.mlp.experts.114.gate_proj",
|
| 1024 |
-
"mtp.layers.0.mlp.experts.114.up_proj",
|
| 1025 |
-
"mtp.layers.0.mlp.experts.115.down_proj",
|
| 1026 |
-
"mtp.layers.0.mlp.experts.115.gate_proj",
|
| 1027 |
-
"mtp.layers.0.mlp.experts.115.up_proj",
|
| 1028 |
-
"mtp.layers.0.mlp.experts.116.down_proj",
|
| 1029 |
-
"mtp.layers.0.mlp.experts.116.gate_proj",
|
| 1030 |
-
"mtp.layers.0.mlp.experts.116.up_proj",
|
| 1031 |
-
"mtp.layers.0.mlp.experts.117.down_proj",
|
| 1032 |
-
"mtp.layers.0.mlp.experts.117.gate_proj",
|
| 1033 |
-
"mtp.layers.0.mlp.experts.117.up_proj",
|
| 1034 |
-
"mtp.layers.0.mlp.experts.118.down_proj",
|
| 1035 |
-
"mtp.layers.0.mlp.experts.118.gate_proj",
|
| 1036 |
-
"mtp.layers.0.mlp.experts.118.up_proj",
|
| 1037 |
-
"mtp.layers.0.mlp.experts.119.down_proj",
|
| 1038 |
-
"mtp.layers.0.mlp.experts.119.gate_proj",
|
| 1039 |
-
"mtp.layers.0.mlp.experts.119.up_proj",
|
| 1040 |
-
"mtp.layers.0.mlp.experts.12.down_proj",
|
| 1041 |
-
"mtp.layers.0.mlp.experts.12.gate_proj",
|
| 1042 |
-
"mtp.layers.0.mlp.experts.12.up_proj",
|
| 1043 |
-
"mtp.layers.0.mlp.experts.120.down_proj",
|
| 1044 |
-
"mtp.layers.0.mlp.experts.120.gate_proj",
|
| 1045 |
-
"mtp.layers.0.mlp.experts.120.up_proj",
|
| 1046 |
-
"mtp.layers.0.mlp.experts.121.down_proj",
|
| 1047 |
-
"mtp.layers.0.mlp.experts.121.gate_proj",
|
| 1048 |
-
"mtp.layers.0.mlp.experts.121.up_proj",
|
| 1049 |
-
"mtp.layers.0.mlp.experts.122.down_proj",
|
| 1050 |
-
"mtp.layers.0.mlp.experts.122.gate_proj",
|
| 1051 |
-
"mtp.layers.0.mlp.experts.122.up_proj",
|
| 1052 |
-
"mtp.layers.0.mlp.experts.123.down_proj",
|
| 1053 |
-
"mtp.layers.0.mlp.experts.123.gate_proj",
|
| 1054 |
-
"mtp.layers.0.mlp.experts.123.up_proj",
|
| 1055 |
-
"mtp.layers.0.mlp.experts.124.down_proj",
|
| 1056 |
-
"mtp.layers.0.mlp.experts.124.gate_proj",
|
| 1057 |
-
"mtp.layers.0.mlp.experts.124.up_proj",
|
| 1058 |
-
"mtp.layers.0.mlp.experts.125.down_proj",
|
| 1059 |
-
"mtp.layers.0.mlp.experts.125.gate_proj",
|
| 1060 |
-
"mtp.layers.0.mlp.experts.125.up_proj",
|
| 1061 |
-
"mtp.layers.0.mlp.experts.126.down_proj",
|
| 1062 |
-
"mtp.layers.0.mlp.experts.126.gate_proj",
|
| 1063 |
-
"mtp.layers.0.mlp.experts.126.up_proj",
|
| 1064 |
-
"mtp.layers.0.mlp.experts.127.down_proj",
|
| 1065 |
-
"mtp.layers.0.mlp.experts.127.gate_proj",
|
| 1066 |
-
"mtp.layers.0.mlp.experts.127.up_proj",
|
| 1067 |
-
"mtp.layers.0.mlp.experts.128.down_proj",
|
| 1068 |
-
"mtp.layers.0.mlp.experts.128.gate_proj",
|
| 1069 |
-
"mtp.layers.0.mlp.experts.128.up_proj",
|
| 1070 |
-
"mtp.layers.0.mlp.experts.129.down_proj",
|
| 1071 |
-
"mtp.layers.0.mlp.experts.129.gate_proj",
|
| 1072 |
-
"mtp.layers.0.mlp.experts.129.up_proj",
|
| 1073 |
-
"mtp.layers.0.mlp.experts.13.down_proj",
|
| 1074 |
-
"mtp.layers.0.mlp.experts.13.gate_proj",
|
| 1075 |
-
"mtp.layers.0.mlp.experts.13.up_proj",
|
| 1076 |
-
"mtp.layers.0.mlp.experts.130.down_proj",
|
| 1077 |
-
"mtp.layers.0.mlp.experts.130.gate_proj",
|
| 1078 |
-
"mtp.layers.0.mlp.experts.130.up_proj",
|
| 1079 |
-
"mtp.layers.0.mlp.experts.131.down_proj",
|
| 1080 |
-
"mtp.layers.0.mlp.experts.131.gate_proj",
|
| 1081 |
-
"mtp.layers.0.mlp.experts.131.up_proj",
|
| 1082 |
-
"mtp.layers.0.mlp.experts.132.down_proj",
|
| 1083 |
-
"mtp.layers.0.mlp.experts.132.gate_proj",
|
| 1084 |
-
"mtp.layers.0.mlp.experts.132.up_proj",
|
| 1085 |
-
"mtp.layers.0.mlp.experts.133.down_proj",
|
| 1086 |
-
"mtp.layers.0.mlp.experts.133.gate_proj",
|
| 1087 |
-
"mtp.layers.0.mlp.experts.133.up_proj",
|
| 1088 |
-
"mtp.layers.0.mlp.experts.134.down_proj",
|
| 1089 |
-
"mtp.layers.0.mlp.experts.134.gate_proj",
|
| 1090 |
-
"mtp.layers.0.mlp.experts.134.up_proj",
|
| 1091 |
-
"mtp.layers.0.mlp.experts.135.down_proj",
|
| 1092 |
-
"mtp.layers.0.mlp.experts.135.gate_proj",
|
| 1093 |
-
"mtp.layers.0.mlp.experts.135.up_proj",
|
| 1094 |
-
"mtp.layers.0.mlp.experts.136.down_proj",
|
| 1095 |
-
"mtp.layers.0.mlp.experts.136.gate_proj",
|
| 1096 |
-
"mtp.layers.0.mlp.experts.136.up_proj",
|
| 1097 |
-
"mtp.layers.0.mlp.experts.137.down_proj",
|
| 1098 |
-
"mtp.layers.0.mlp.experts.137.gate_proj",
|
| 1099 |
-
"mtp.layers.0.mlp.experts.137.up_proj",
|
| 1100 |
-
"mtp.layers.0.mlp.experts.138.down_proj",
|
| 1101 |
-
"mtp.layers.0.mlp.experts.138.gate_proj",
|
| 1102 |
-
"mtp.layers.0.mlp.experts.138.up_proj",
|
| 1103 |
-
"mtp.layers.0.mlp.experts.139.down_proj",
|
| 1104 |
-
"mtp.layers.0.mlp.experts.139.gate_proj",
|
| 1105 |
-
"mtp.layers.0.mlp.experts.139.up_proj",
|
| 1106 |
-
"mtp.layers.0.mlp.experts.14.down_proj",
|
| 1107 |
-
"mtp.layers.0.mlp.experts.14.gate_proj",
|
| 1108 |
-
"mtp.layers.0.mlp.experts.14.up_proj",
|
| 1109 |
-
"mtp.layers.0.mlp.experts.140.down_proj",
|
| 1110 |
-
"mtp.layers.0.mlp.experts.140.gate_proj",
|
| 1111 |
-
"mtp.layers.0.mlp.experts.140.up_proj",
|
| 1112 |
-
"mtp.layers.0.mlp.experts.141.down_proj",
|
| 1113 |
-
"mtp.layers.0.mlp.experts.141.gate_proj",
|
| 1114 |
-
"mtp.layers.0.mlp.experts.141.up_proj",
|
| 1115 |
-
"mtp.layers.0.mlp.experts.142.down_proj",
|
| 1116 |
-
"mtp.layers.0.mlp.experts.142.gate_proj",
|
| 1117 |
-
"mtp.layers.0.mlp.experts.142.up_proj",
|
| 1118 |
-
"mtp.layers.0.mlp.experts.143.down_proj",
|
| 1119 |
-
"mtp.layers.0.mlp.experts.143.gate_proj",
|
| 1120 |
-
"mtp.layers.0.mlp.experts.143.up_proj",
|
| 1121 |
-
"mtp.layers.0.mlp.experts.144.down_proj",
|
| 1122 |
-
"mtp.layers.0.mlp.experts.144.gate_proj",
|
| 1123 |
-
"mtp.layers.0.mlp.experts.144.up_proj",
|
| 1124 |
-
"mtp.layers.0.mlp.experts.145.down_proj",
|
| 1125 |
-
"mtp.layers.0.mlp.experts.145.gate_proj",
|
| 1126 |
-
"mtp.layers.0.mlp.experts.145.up_proj",
|
| 1127 |
-
"mtp.layers.0.mlp.experts.146.down_proj",
|
| 1128 |
-
"mtp.layers.0.mlp.experts.146.gate_proj",
|
| 1129 |
-
"mtp.layers.0.mlp.experts.146.up_proj",
|
| 1130 |
-
"mtp.layers.0.mlp.experts.147.down_proj",
|
| 1131 |
-
"mtp.layers.0.mlp.experts.147.gate_proj",
|
| 1132 |
-
"mtp.layers.0.mlp.experts.147.up_proj",
|
| 1133 |
-
"mtp.layers.0.mlp.experts.148.down_proj",
|
| 1134 |
-
"mtp.layers.0.mlp.experts.148.gate_proj",
|
| 1135 |
-
"mtp.layers.0.mlp.experts.148.up_proj",
|
| 1136 |
-
"mtp.layers.0.mlp.experts.149.down_proj",
|
| 1137 |
-
"mtp.layers.0.mlp.experts.149.gate_proj",
|
| 1138 |
-
"mtp.layers.0.mlp.experts.149.up_proj",
|
| 1139 |
-
"mtp.layers.0.mlp.experts.15.down_proj",
|
| 1140 |
-
"mtp.layers.0.mlp.experts.15.gate_proj",
|
| 1141 |
-
"mtp.layers.0.mlp.experts.15.up_proj",
|
| 1142 |
-
"mtp.layers.0.mlp.experts.150.down_proj",
|
| 1143 |
-
"mtp.layers.0.mlp.experts.150.gate_proj",
|
| 1144 |
-
"mtp.layers.0.mlp.experts.150.up_proj",
|
| 1145 |
-
"mtp.layers.0.mlp.experts.151.down_proj",
|
| 1146 |
-
"mtp.layers.0.mlp.experts.151.gate_proj",
|
| 1147 |
-
"mtp.layers.0.mlp.experts.151.up_proj",
|
| 1148 |
-
"mtp.layers.0.mlp.experts.152.down_proj",
|
| 1149 |
-
"mtp.layers.0.mlp.experts.152.gate_proj",
|
| 1150 |
-
"mtp.layers.0.mlp.experts.152.up_proj",
|
| 1151 |
-
"mtp.layers.0.mlp.experts.153.down_proj",
|
| 1152 |
-
"mtp.layers.0.mlp.experts.153.gate_proj",
|
| 1153 |
-
"mtp.layers.0.mlp.experts.153.up_proj",
|
| 1154 |
-
"mtp.layers.0.mlp.experts.154.down_proj",
|
| 1155 |
-
"mtp.layers.0.mlp.experts.154.gate_proj",
|
| 1156 |
-
"mtp.layers.0.mlp.experts.154.up_proj",
|
| 1157 |
-
"mtp.layers.0.mlp.experts.155.down_proj",
|
| 1158 |
-
"mtp.layers.0.mlp.experts.155.gate_proj",
|
| 1159 |
-
"mtp.layers.0.mlp.experts.155.up_proj",
|
| 1160 |
-
"mtp.layers.0.mlp.experts.156.down_proj",
|
| 1161 |
-
"mtp.layers.0.mlp.experts.156.gate_proj",
|
| 1162 |
-
"mtp.layers.0.mlp.experts.156.up_proj",
|
| 1163 |
-
"mtp.layers.0.mlp.experts.157.down_proj",
|
| 1164 |
-
"mtp.layers.0.mlp.experts.157.gate_proj",
|
| 1165 |
-
"mtp.layers.0.mlp.experts.157.up_proj",
|
| 1166 |
-
"mtp.layers.0.mlp.experts.158.down_proj",
|
| 1167 |
-
"mtp.layers.0.mlp.experts.158.gate_proj",
|
| 1168 |
-
"mtp.layers.0.mlp.experts.158.up_proj",
|
| 1169 |
-
"mtp.layers.0.mlp.experts.159.down_proj",
|
| 1170 |
-
"mtp.layers.0.mlp.experts.159.gate_proj",
|
| 1171 |
-
"mtp.layers.0.mlp.experts.159.up_proj",
|
| 1172 |
-
"mtp.layers.0.mlp.experts.16.down_proj",
|
| 1173 |
-
"mtp.layers.0.mlp.experts.16.gate_proj",
|
| 1174 |
-
"mtp.layers.0.mlp.experts.16.up_proj",
|
| 1175 |
-
"mtp.layers.0.mlp.experts.160.down_proj",
|
| 1176 |
-
"mtp.layers.0.mlp.experts.160.gate_proj",
|
| 1177 |
-
"mtp.layers.0.mlp.experts.160.up_proj",
|
| 1178 |
-
"mtp.layers.0.mlp.experts.161.down_proj",
|
| 1179 |
-
"mtp.layers.0.mlp.experts.161.gate_proj",
|
| 1180 |
-
"mtp.layers.0.mlp.experts.161.up_proj",
|
| 1181 |
-
"mtp.layers.0.mlp.experts.162.down_proj",
|
| 1182 |
-
"mtp.layers.0.mlp.experts.162.gate_proj",
|
| 1183 |
-
"mtp.layers.0.mlp.experts.162.up_proj",
|
| 1184 |
-
"mtp.layers.0.mlp.experts.163.down_proj",
|
| 1185 |
-
"mtp.layers.0.mlp.experts.163.gate_proj",
|
| 1186 |
-
"mtp.layers.0.mlp.experts.163.up_proj",
|
| 1187 |
-
"mtp.layers.0.mlp.experts.164.down_proj",
|
| 1188 |
-
"mtp.layers.0.mlp.experts.164.gate_proj",
|
| 1189 |
-
"mtp.layers.0.mlp.experts.164.up_proj",
|
| 1190 |
-
"mtp.layers.0.mlp.experts.165.down_proj",
|
| 1191 |
-
"mtp.layers.0.mlp.experts.165.gate_proj",
|
| 1192 |
-
"mtp.layers.0.mlp.experts.165.up_proj",
|
| 1193 |
-
"mtp.layers.0.mlp.experts.166.down_proj",
|
| 1194 |
-
"mtp.layers.0.mlp.experts.166.gate_proj",
|
| 1195 |
-
"mtp.layers.0.mlp.experts.166.up_proj",
|
| 1196 |
-
"mtp.layers.0.mlp.experts.167.down_proj",
|
| 1197 |
-
"mtp.layers.0.mlp.experts.167.gate_proj",
|
| 1198 |
-
"mtp.layers.0.mlp.experts.167.up_proj",
|
| 1199 |
-
"mtp.layers.0.mlp.experts.168.down_proj",
|
| 1200 |
-
"mtp.layers.0.mlp.experts.168.gate_proj",
|
| 1201 |
-
"mtp.layers.0.mlp.experts.168.up_proj",
|
| 1202 |
-
"mtp.layers.0.mlp.experts.169.down_proj",
|
| 1203 |
-
"mtp.layers.0.mlp.experts.169.gate_proj",
|
| 1204 |
-
"mtp.layers.0.mlp.experts.169.up_proj",
|
| 1205 |
-
"mtp.layers.0.mlp.experts.17.down_proj",
|
| 1206 |
-
"mtp.layers.0.mlp.experts.17.gate_proj",
|
| 1207 |
-
"mtp.layers.0.mlp.experts.17.up_proj",
|
| 1208 |
-
"mtp.layers.0.mlp.experts.170.down_proj",
|
| 1209 |
-
"mtp.layers.0.mlp.experts.170.gate_proj",
|
| 1210 |
-
"mtp.layers.0.mlp.experts.170.up_proj",
|
| 1211 |
-
"mtp.layers.0.mlp.experts.171.down_proj",
|
| 1212 |
-
"mtp.layers.0.mlp.experts.171.gate_proj",
|
| 1213 |
-
"mtp.layers.0.mlp.experts.171.up_proj",
|
| 1214 |
-
"mtp.layers.0.mlp.experts.172.down_proj",
|
| 1215 |
-
"mtp.layers.0.mlp.experts.172.gate_proj",
|
| 1216 |
-
"mtp.layers.0.mlp.experts.172.up_proj",
|
| 1217 |
-
"mtp.layers.0.mlp.experts.173.down_proj",
|
| 1218 |
-
"mtp.layers.0.mlp.experts.173.gate_proj",
|
| 1219 |
-
"mtp.layers.0.mlp.experts.173.up_proj",
|
| 1220 |
-
"mtp.layers.0.mlp.experts.174.down_proj",
|
| 1221 |
-
"mtp.layers.0.mlp.experts.174.gate_proj",
|
| 1222 |
-
"mtp.layers.0.mlp.experts.174.up_proj",
|
| 1223 |
-
"mtp.layers.0.mlp.experts.175.down_proj",
|
| 1224 |
-
"mtp.layers.0.mlp.experts.175.gate_proj",
|
| 1225 |
-
"mtp.layers.0.mlp.experts.175.up_proj",
|
| 1226 |
-
"mtp.layers.0.mlp.experts.176.down_proj",
|
| 1227 |
-
"mtp.layers.0.mlp.experts.176.gate_proj",
|
| 1228 |
-
"mtp.layers.0.mlp.experts.176.up_proj",
|
| 1229 |
-
"mtp.layers.0.mlp.experts.177.down_proj",
|
| 1230 |
-
"mtp.layers.0.mlp.experts.177.gate_proj",
|
| 1231 |
-
"mtp.layers.0.mlp.experts.177.up_proj",
|
| 1232 |
-
"mtp.layers.0.mlp.experts.178.down_proj",
|
| 1233 |
-
"mtp.layers.0.mlp.experts.178.gate_proj",
|
| 1234 |
-
"mtp.layers.0.mlp.experts.178.up_proj",
|
| 1235 |
-
"mtp.layers.0.mlp.experts.179.down_proj",
|
| 1236 |
-
"mtp.layers.0.mlp.experts.179.gate_proj",
|
| 1237 |
-
"mtp.layers.0.mlp.experts.179.up_proj",
|
| 1238 |
-
"mtp.layers.0.mlp.experts.18.down_proj",
|
| 1239 |
-
"mtp.layers.0.mlp.experts.18.gate_proj",
|
| 1240 |
-
"mtp.layers.0.mlp.experts.18.up_proj",
|
| 1241 |
-
"mtp.layers.0.mlp.experts.180.down_proj",
|
| 1242 |
-
"mtp.layers.0.mlp.experts.180.gate_proj",
|
| 1243 |
-
"mtp.layers.0.mlp.experts.180.up_proj",
|
| 1244 |
-
"mtp.layers.0.mlp.experts.181.down_proj",
|
| 1245 |
-
"mtp.layers.0.mlp.experts.181.gate_proj",
|
| 1246 |
-
"mtp.layers.0.mlp.experts.181.up_proj",
|
| 1247 |
-
"mtp.layers.0.mlp.experts.182.down_proj",
|
| 1248 |
-
"mtp.layers.0.mlp.experts.182.gate_proj",
|
| 1249 |
-
"mtp.layers.0.mlp.experts.182.up_proj",
|
| 1250 |
-
"mtp.layers.0.mlp.experts.183.down_proj",
|
| 1251 |
-
"mtp.layers.0.mlp.experts.183.gate_proj",
|
| 1252 |
-
"mtp.layers.0.mlp.experts.183.up_proj",
|
| 1253 |
-
"mtp.layers.0.mlp.experts.184.down_proj",
|
| 1254 |
-
"mtp.layers.0.mlp.experts.184.gate_proj",
|
| 1255 |
-
"mtp.layers.0.mlp.experts.184.up_proj",
|
| 1256 |
-
"mtp.layers.0.mlp.experts.185.down_proj",
|
| 1257 |
-
"mtp.layers.0.mlp.experts.185.gate_proj",
|
| 1258 |
-
"mtp.layers.0.mlp.experts.185.up_proj",
|
| 1259 |
-
"mtp.layers.0.mlp.experts.186.down_proj",
|
| 1260 |
-
"mtp.layers.0.mlp.experts.186.gate_proj",
|
| 1261 |
-
"mtp.layers.0.mlp.experts.186.up_proj",
|
| 1262 |
-
"mtp.layers.0.mlp.experts.187.down_proj",
|
| 1263 |
-
"mtp.layers.0.mlp.experts.187.gate_proj",
|
| 1264 |
-
"mtp.layers.0.mlp.experts.187.up_proj",
|
| 1265 |
-
"mtp.layers.0.mlp.experts.188.down_proj",
|
| 1266 |
-
"mtp.layers.0.mlp.experts.188.gate_proj",
|
| 1267 |
-
"mtp.layers.0.mlp.experts.188.up_proj",
|
| 1268 |
-
"mtp.layers.0.mlp.experts.189.down_proj",
|
| 1269 |
-
"mtp.layers.0.mlp.experts.189.gate_proj",
|
| 1270 |
-
"mtp.layers.0.mlp.experts.189.up_proj",
|
| 1271 |
-
"mtp.layers.0.mlp.experts.19.down_proj",
|
| 1272 |
-
"mtp.layers.0.mlp.experts.19.gate_proj",
|
| 1273 |
-
"mtp.layers.0.mlp.experts.19.up_proj",
|
| 1274 |
-
"mtp.layers.0.mlp.experts.190.down_proj",
|
| 1275 |
-
"mtp.layers.0.mlp.experts.190.gate_proj",
|
| 1276 |
-
"mtp.layers.0.mlp.experts.190.up_proj",
|
| 1277 |
-
"mtp.layers.0.mlp.experts.191.down_proj",
|
| 1278 |
-
"mtp.layers.0.mlp.experts.191.gate_proj",
|
| 1279 |
-
"mtp.layers.0.mlp.experts.191.up_proj",
|
| 1280 |
-
"mtp.layers.0.mlp.experts.192.down_proj",
|
| 1281 |
-
"mtp.layers.0.mlp.experts.192.gate_proj",
|
| 1282 |
-
"mtp.layers.0.mlp.experts.192.up_proj",
|
| 1283 |
-
"mtp.layers.0.mlp.experts.193.down_proj",
|
| 1284 |
-
"mtp.layers.0.mlp.experts.193.gate_proj",
|
| 1285 |
-
"mtp.layers.0.mlp.experts.193.up_proj",
|
| 1286 |
-
"mtp.layers.0.mlp.experts.194.down_proj",
|
| 1287 |
-
"mtp.layers.0.mlp.experts.194.gate_proj",
|
| 1288 |
-
"mtp.layers.0.mlp.experts.194.up_proj",
|
| 1289 |
-
"mtp.layers.0.mlp.experts.195.down_proj",
|
| 1290 |
-
"mtp.layers.0.mlp.experts.195.gate_proj",
|
| 1291 |
-
"mtp.layers.0.mlp.experts.195.up_proj",
|
| 1292 |
-
"mtp.layers.0.mlp.experts.196.down_proj",
|
| 1293 |
-
"mtp.layers.0.mlp.experts.196.gate_proj",
|
| 1294 |
-
"mtp.layers.0.mlp.experts.196.up_proj",
|
| 1295 |
-
"mtp.layers.0.mlp.experts.197.down_proj",
|
| 1296 |
-
"mtp.layers.0.mlp.experts.197.gate_proj",
|
| 1297 |
-
"mtp.layers.0.mlp.experts.197.up_proj",
|
| 1298 |
-
"mtp.layers.0.mlp.experts.198.down_proj",
|
| 1299 |
-
"mtp.layers.0.mlp.experts.198.gate_proj",
|
| 1300 |
-
"mtp.layers.0.mlp.experts.198.up_proj",
|
| 1301 |
-
"mtp.layers.0.mlp.experts.199.down_proj",
|
| 1302 |
-
"mtp.layers.0.mlp.experts.199.gate_proj",
|
| 1303 |
-
"mtp.layers.0.mlp.experts.199.up_proj",
|
| 1304 |
-
"mtp.layers.0.mlp.experts.2.down_proj",
|
| 1305 |
-
"mtp.layers.0.mlp.experts.2.gate_proj",
|
| 1306 |
-
"mtp.layers.0.mlp.experts.2.up_proj",
|
| 1307 |
-
"mtp.layers.0.mlp.experts.20.down_proj",
|
| 1308 |
-
"mtp.layers.0.mlp.experts.20.gate_proj",
|
| 1309 |
-
"mtp.layers.0.mlp.experts.20.up_proj",
|
| 1310 |
-
"mtp.layers.0.mlp.experts.200.down_proj",
|
| 1311 |
-
"mtp.layers.0.mlp.experts.200.gate_proj",
|
| 1312 |
-
"mtp.layers.0.mlp.experts.200.up_proj",
|
| 1313 |
-
"mtp.layers.0.mlp.experts.201.down_proj",
|
| 1314 |
-
"mtp.layers.0.mlp.experts.201.gate_proj",
|
| 1315 |
-
"mtp.layers.0.mlp.experts.201.up_proj",
|
| 1316 |
-
"mtp.layers.0.mlp.experts.202.down_proj",
|
| 1317 |
-
"mtp.layers.0.mlp.experts.202.gate_proj",
|
| 1318 |
-
"mtp.layers.0.mlp.experts.202.up_proj",
|
| 1319 |
-
"mtp.layers.0.mlp.experts.203.down_proj",
|
| 1320 |
-
"mtp.layers.0.mlp.experts.203.gate_proj",
|
| 1321 |
-
"mtp.layers.0.mlp.experts.203.up_proj",
|
| 1322 |
-
"mtp.layers.0.mlp.experts.204.down_proj",
|
| 1323 |
-
"mtp.layers.0.mlp.experts.204.gate_proj",
|
| 1324 |
-
"mtp.layers.0.mlp.experts.204.up_proj",
|
| 1325 |
-
"mtp.layers.0.mlp.experts.205.down_proj",
|
| 1326 |
-
"mtp.layers.0.mlp.experts.205.gate_proj",
|
| 1327 |
-
"mtp.layers.0.mlp.experts.205.up_proj",
|
| 1328 |
-
"mtp.layers.0.mlp.experts.206.down_proj",
|
| 1329 |
-
"mtp.layers.0.mlp.experts.206.gate_proj",
|
| 1330 |
-
"mtp.layers.0.mlp.experts.206.up_proj",
|
| 1331 |
-
"mtp.layers.0.mlp.experts.207.down_proj",
|
| 1332 |
-
"mtp.layers.0.mlp.experts.207.gate_proj",
|
| 1333 |
-
"mtp.layers.0.mlp.experts.207.up_proj",
|
| 1334 |
-
"mtp.layers.0.mlp.experts.208.down_proj",
|
| 1335 |
-
"mtp.layers.0.mlp.experts.208.gate_proj",
|
| 1336 |
-
"mtp.layers.0.mlp.experts.208.up_proj",
|
| 1337 |
-
"mtp.layers.0.mlp.experts.209.down_proj",
|
| 1338 |
-
"mtp.layers.0.mlp.experts.209.gate_proj",
|
| 1339 |
-
"mtp.layers.0.mlp.experts.209.up_proj",
|
| 1340 |
-
"mtp.layers.0.mlp.experts.21.down_proj",
|
| 1341 |
-
"mtp.layers.0.mlp.experts.21.gate_proj",
|
| 1342 |
-
"mtp.layers.0.mlp.experts.21.up_proj",
|
| 1343 |
-
"mtp.layers.0.mlp.experts.210.down_proj",
|
| 1344 |
-
"mtp.layers.0.mlp.experts.210.gate_proj",
|
| 1345 |
-
"mtp.layers.0.mlp.experts.210.up_proj",
|
| 1346 |
-
"mtp.layers.0.mlp.experts.211.down_proj",
|
| 1347 |
-
"mtp.layers.0.mlp.experts.211.gate_proj",
|
| 1348 |
-
"mtp.layers.0.mlp.experts.211.up_proj",
|
| 1349 |
-
"mtp.layers.0.mlp.experts.212.down_proj",
|
| 1350 |
-
"mtp.layers.0.mlp.experts.212.gate_proj",
|
| 1351 |
-
"mtp.layers.0.mlp.experts.212.up_proj",
|
| 1352 |
-
"mtp.layers.0.mlp.experts.213.down_proj",
|
| 1353 |
-
"mtp.layers.0.mlp.experts.213.gate_proj",
|
| 1354 |
-
"mtp.layers.0.mlp.experts.213.up_proj",
|
| 1355 |
-
"mtp.layers.0.mlp.experts.214.down_proj",
|
| 1356 |
-
"mtp.layers.0.mlp.experts.214.gate_proj",
|
| 1357 |
-
"mtp.layers.0.mlp.experts.214.up_proj",
|
| 1358 |
-
"mtp.layers.0.mlp.experts.215.down_proj",
|
| 1359 |
-
"mtp.layers.0.mlp.experts.215.gate_proj",
|
| 1360 |
-
"mtp.layers.0.mlp.experts.215.up_proj",
|
| 1361 |
-
"mtp.layers.0.mlp.experts.216.down_proj",
|
| 1362 |
-
"mtp.layers.0.mlp.experts.216.gate_proj",
|
| 1363 |
-
"mtp.layers.0.mlp.experts.216.up_proj",
|
| 1364 |
-
"mtp.layers.0.mlp.experts.217.down_proj",
|
| 1365 |
-
"mtp.layers.0.mlp.experts.217.gate_proj",
|
| 1366 |
-
"mtp.layers.0.mlp.experts.217.up_proj",
|
| 1367 |
-
"mtp.layers.0.mlp.experts.218.down_proj",
|
| 1368 |
-
"mtp.layers.0.mlp.experts.218.gate_proj",
|
| 1369 |
-
"mtp.layers.0.mlp.experts.218.up_proj",
|
| 1370 |
-
"mtp.layers.0.mlp.experts.219.down_proj",
|
| 1371 |
-
"mtp.layers.0.mlp.experts.219.gate_proj",
|
| 1372 |
-
"mtp.layers.0.mlp.experts.219.up_proj",
|
| 1373 |
-
"mtp.layers.0.mlp.experts.22.down_proj",
|
| 1374 |
-
"mtp.layers.0.mlp.experts.22.gate_proj",
|
| 1375 |
-
"mtp.layers.0.mlp.experts.22.up_proj",
|
| 1376 |
-
"mtp.layers.0.mlp.experts.220.down_proj",
|
| 1377 |
-
"mtp.layers.0.mlp.experts.220.gate_proj",
|
| 1378 |
-
"mtp.layers.0.mlp.experts.220.up_proj",
|
| 1379 |
-
"mtp.layers.0.mlp.experts.221.down_proj",
|
| 1380 |
-
"mtp.layers.0.mlp.experts.221.gate_proj",
|
| 1381 |
-
"mtp.layers.0.mlp.experts.221.up_proj",
|
| 1382 |
-
"mtp.layers.0.mlp.experts.222.down_proj",
|
| 1383 |
-
"mtp.layers.0.mlp.experts.222.gate_proj",
|
| 1384 |
-
"mtp.layers.0.mlp.experts.222.up_proj",
|
| 1385 |
-
"mtp.layers.0.mlp.experts.223.down_proj",
|
| 1386 |
-
"mtp.layers.0.mlp.experts.223.gate_proj",
|
| 1387 |
-
"mtp.layers.0.mlp.experts.223.up_proj",
|
| 1388 |
-
"mtp.layers.0.mlp.experts.224.down_proj",
|
| 1389 |
-
"mtp.layers.0.mlp.experts.224.gate_proj",
|
| 1390 |
-
"mtp.layers.0.mlp.experts.224.up_proj",
|
| 1391 |
-
"mtp.layers.0.mlp.experts.225.down_proj",
|
| 1392 |
-
"mtp.layers.0.mlp.experts.225.gate_proj",
|
| 1393 |
-
"mtp.layers.0.mlp.experts.225.up_proj",
|
| 1394 |
-
"mtp.layers.0.mlp.experts.226.down_proj",
|
| 1395 |
-
"mtp.layers.0.mlp.experts.226.gate_proj",
|
| 1396 |
-
"mtp.layers.0.mlp.experts.226.up_proj",
|
| 1397 |
-
"mtp.layers.0.mlp.experts.227.down_proj",
|
| 1398 |
-
"mtp.layers.0.mlp.experts.227.gate_proj",
|
| 1399 |
-
"mtp.layers.0.mlp.experts.227.up_proj",
|
| 1400 |
-
"mtp.layers.0.mlp.experts.228.down_proj",
|
| 1401 |
-
"mtp.layers.0.mlp.experts.228.gate_proj",
|
| 1402 |
-
"mtp.layers.0.mlp.experts.228.up_proj",
|
| 1403 |
-
"mtp.layers.0.mlp.experts.229.down_proj",
|
| 1404 |
-
"mtp.layers.0.mlp.experts.229.gate_proj",
|
| 1405 |
-
"mtp.layers.0.mlp.experts.229.up_proj",
|
| 1406 |
-
"mtp.layers.0.mlp.experts.23.down_proj",
|
| 1407 |
-
"mtp.layers.0.mlp.experts.23.gate_proj",
|
| 1408 |
-
"mtp.layers.0.mlp.experts.23.up_proj",
|
| 1409 |
-
"mtp.layers.0.mlp.experts.230.down_proj",
|
| 1410 |
-
"mtp.layers.0.mlp.experts.230.gate_proj",
|
| 1411 |
-
"mtp.layers.0.mlp.experts.230.up_proj",
|
| 1412 |
-
"mtp.layers.0.mlp.experts.231.down_proj",
|
| 1413 |
-
"mtp.layers.0.mlp.experts.231.gate_proj",
|
| 1414 |
-
"mtp.layers.0.mlp.experts.231.up_proj",
|
| 1415 |
-
"mtp.layers.0.mlp.experts.232.down_proj",
|
| 1416 |
-
"mtp.layers.0.mlp.experts.232.gate_proj",
|
| 1417 |
-
"mtp.layers.0.mlp.experts.232.up_proj",
|
| 1418 |
-
"mtp.layers.0.mlp.experts.233.down_proj",
|
| 1419 |
-
"mtp.layers.0.mlp.experts.233.gate_proj",
|
| 1420 |
-
"mtp.layers.0.mlp.experts.233.up_proj",
|
| 1421 |
-
"mtp.layers.0.mlp.experts.234.down_proj",
|
| 1422 |
-
"mtp.layers.0.mlp.experts.234.gate_proj",
|
| 1423 |
-
"mtp.layers.0.mlp.experts.234.up_proj",
|
| 1424 |
-
"mtp.layers.0.mlp.experts.235.down_proj",
|
| 1425 |
-
"mtp.layers.0.mlp.experts.235.gate_proj",
|
| 1426 |
-
"mtp.layers.0.mlp.experts.235.up_proj",
|
| 1427 |
-
"mtp.layers.0.mlp.experts.236.down_proj",
|
| 1428 |
-
"mtp.layers.0.mlp.experts.236.gate_proj",
|
| 1429 |
-
"mtp.layers.0.mlp.experts.236.up_proj",
|
| 1430 |
-
"mtp.layers.0.mlp.experts.237.down_proj",
|
| 1431 |
-
"mtp.layers.0.mlp.experts.237.gate_proj",
|
| 1432 |
-
"mtp.layers.0.mlp.experts.237.up_proj",
|
| 1433 |
-
"mtp.layers.0.mlp.experts.238.down_proj",
|
| 1434 |
-
"mtp.layers.0.mlp.experts.238.gate_proj",
|
| 1435 |
-
"mtp.layers.0.mlp.experts.238.up_proj",
|
| 1436 |
-
"mtp.layers.0.mlp.experts.239.down_proj",
|
| 1437 |
-
"mtp.layers.0.mlp.experts.239.gate_proj",
|
| 1438 |
-
"mtp.layers.0.mlp.experts.239.up_proj",
|
| 1439 |
-
"mtp.layers.0.mlp.experts.24.down_proj",
|
| 1440 |
-
"mtp.layers.0.mlp.experts.24.gate_proj",
|
| 1441 |
-
"mtp.layers.0.mlp.experts.24.up_proj",
|
| 1442 |
-
"mtp.layers.0.mlp.experts.240.down_proj",
|
| 1443 |
-
"mtp.layers.0.mlp.experts.240.gate_proj",
|
| 1444 |
-
"mtp.layers.0.mlp.experts.240.up_proj",
|
| 1445 |
-
"mtp.layers.0.mlp.experts.241.down_proj",
|
| 1446 |
-
"mtp.layers.0.mlp.experts.241.gate_proj",
|
| 1447 |
-
"mtp.layers.0.mlp.experts.241.up_proj",
|
| 1448 |
-
"mtp.layers.0.mlp.experts.242.down_proj",
|
| 1449 |
-
"mtp.layers.0.mlp.experts.242.gate_proj",
|
| 1450 |
-
"mtp.layers.0.mlp.experts.242.up_proj",
|
| 1451 |
-
"mtp.layers.0.mlp.experts.243.down_proj",
|
| 1452 |
-
"mtp.layers.0.mlp.experts.243.gate_proj",
|
| 1453 |
-
"mtp.layers.0.mlp.experts.243.up_proj",
|
| 1454 |
-
"mtp.layers.0.mlp.experts.244.down_proj",
|
| 1455 |
-
"mtp.layers.0.mlp.experts.244.gate_proj",
|
| 1456 |
-
"mtp.layers.0.mlp.experts.244.up_proj",
|
| 1457 |
-
"mtp.layers.0.mlp.experts.245.down_proj",
|
| 1458 |
-
"mtp.layers.0.mlp.experts.245.gate_proj",
|
| 1459 |
-
"mtp.layers.0.mlp.experts.245.up_proj",
|
| 1460 |
-
"mtp.layers.0.mlp.experts.246.down_proj",
|
| 1461 |
-
"mtp.layers.0.mlp.experts.246.gate_proj",
|
| 1462 |
-
"mtp.layers.0.mlp.experts.246.up_proj",
|
| 1463 |
-
"mtp.layers.0.mlp.experts.247.down_proj",
|
| 1464 |
-
"mtp.layers.0.mlp.experts.247.gate_proj",
|
| 1465 |
-
"mtp.layers.0.mlp.experts.247.up_proj",
|
| 1466 |
-
"mtp.layers.0.mlp.experts.248.down_proj",
|
| 1467 |
-
"mtp.layers.0.mlp.experts.248.gate_proj",
|
| 1468 |
-
"mtp.layers.0.mlp.experts.248.up_proj",
|
| 1469 |
-
"mtp.layers.0.mlp.experts.249.down_proj",
|
| 1470 |
-
"mtp.layers.0.mlp.experts.249.gate_proj",
|
| 1471 |
-
"mtp.layers.0.mlp.experts.249.up_proj",
|
| 1472 |
-
"mtp.layers.0.mlp.experts.25.down_proj",
|
| 1473 |
-
"mtp.layers.0.mlp.experts.25.gate_proj",
|
| 1474 |
-
"mtp.layers.0.mlp.experts.25.up_proj",
|
| 1475 |
-
"mtp.layers.0.mlp.experts.250.down_proj",
|
| 1476 |
-
"mtp.layers.0.mlp.experts.250.gate_proj",
|
| 1477 |
-
"mtp.layers.0.mlp.experts.250.up_proj",
|
| 1478 |
-
"mtp.layers.0.mlp.experts.251.down_proj",
|
| 1479 |
-
"mtp.layers.0.mlp.experts.251.gate_proj",
|
| 1480 |
-
"mtp.layers.0.mlp.experts.251.up_proj",
|
| 1481 |
-
"mtp.layers.0.mlp.experts.252.down_proj",
|
| 1482 |
-
"mtp.layers.0.mlp.experts.252.gate_proj",
|
| 1483 |
-
"mtp.layers.0.mlp.experts.252.up_proj",
|
| 1484 |
-
"mtp.layers.0.mlp.experts.253.down_proj",
|
| 1485 |
-
"mtp.layers.0.mlp.experts.253.gate_proj",
|
| 1486 |
-
"mtp.layers.0.mlp.experts.253.up_proj",
|
| 1487 |
-
"mtp.layers.0.mlp.experts.254.down_proj",
|
| 1488 |
-
"mtp.layers.0.mlp.experts.254.gate_proj",
|
| 1489 |
-
"mtp.layers.0.mlp.experts.254.up_proj",
|
| 1490 |
-
"mtp.layers.0.mlp.experts.255.down_proj",
|
| 1491 |
-
"mtp.layers.0.mlp.experts.255.gate_proj",
|
| 1492 |
-
"mtp.layers.0.mlp.experts.255.up_proj",
|
| 1493 |
-
"mtp.layers.0.mlp.experts.256.down_proj",
|
| 1494 |
-
"mtp.layers.0.mlp.experts.256.gate_proj",
|
| 1495 |
-
"mtp.layers.0.mlp.experts.256.up_proj",
|
| 1496 |
-
"mtp.layers.0.mlp.experts.257.down_proj",
|
| 1497 |
-
"mtp.layers.0.mlp.experts.257.gate_proj",
|
| 1498 |
-
"mtp.layers.0.mlp.experts.257.up_proj",
|
| 1499 |
-
"mtp.layers.0.mlp.experts.258.down_proj",
|
| 1500 |
-
"mtp.layers.0.mlp.experts.258.gate_proj",
|
| 1501 |
-
"mtp.layers.0.mlp.experts.258.up_proj",
|
| 1502 |
-
"mtp.layers.0.mlp.experts.259.down_proj",
|
| 1503 |
-
"mtp.layers.0.mlp.experts.259.gate_proj",
|
| 1504 |
-
"mtp.layers.0.mlp.experts.259.up_proj",
|
| 1505 |
-
"mtp.layers.0.mlp.experts.26.down_proj",
|
| 1506 |
-
"mtp.layers.0.mlp.experts.26.gate_proj",
|
| 1507 |
-
"mtp.layers.0.mlp.experts.26.up_proj",
|
| 1508 |
-
"mtp.layers.0.mlp.experts.260.down_proj",
|
| 1509 |
-
"mtp.layers.0.mlp.experts.260.gate_proj",
|
| 1510 |
-
"mtp.layers.0.mlp.experts.260.up_proj",
|
| 1511 |
-
"mtp.layers.0.mlp.experts.261.down_proj",
|
| 1512 |
-
"mtp.layers.0.mlp.experts.261.gate_proj",
|
| 1513 |
-
"mtp.layers.0.mlp.experts.261.up_proj",
|
| 1514 |
-
"mtp.layers.0.mlp.experts.262.down_proj",
|
| 1515 |
-
"mtp.layers.0.mlp.experts.262.gate_proj",
|
| 1516 |
-
"mtp.layers.0.mlp.experts.262.up_proj",
|
| 1517 |
-
"mtp.layers.0.mlp.experts.263.down_proj",
|
| 1518 |
-
"mtp.layers.0.mlp.experts.263.gate_proj",
|
| 1519 |
-
"mtp.layers.0.mlp.experts.263.up_proj",
|
| 1520 |
-
"mtp.layers.0.mlp.experts.264.down_proj",
|
| 1521 |
-
"mtp.layers.0.mlp.experts.264.gate_proj",
|
| 1522 |
-
"mtp.layers.0.mlp.experts.264.up_proj",
|
| 1523 |
-
"mtp.layers.0.mlp.experts.265.down_proj",
|
| 1524 |
-
"mtp.layers.0.mlp.experts.265.gate_proj",
|
| 1525 |
-
"mtp.layers.0.mlp.experts.265.up_proj",
|
| 1526 |
-
"mtp.layers.0.mlp.experts.266.down_proj",
|
| 1527 |
-
"mtp.layers.0.mlp.experts.266.gate_proj",
|
| 1528 |
-
"mtp.layers.0.mlp.experts.266.up_proj",
|
| 1529 |
-
"mtp.layers.0.mlp.experts.267.down_proj",
|
| 1530 |
-
"mtp.layers.0.mlp.experts.267.gate_proj",
|
| 1531 |
-
"mtp.layers.0.mlp.experts.267.up_proj",
|
| 1532 |
-
"mtp.layers.0.mlp.experts.268.down_proj",
|
| 1533 |
-
"mtp.layers.0.mlp.experts.268.gate_proj",
|
| 1534 |
-
"mtp.layers.0.mlp.experts.268.up_proj",
|
| 1535 |
-
"mtp.layers.0.mlp.experts.269.down_proj",
|
| 1536 |
-
"mtp.layers.0.mlp.experts.269.gate_proj",
|
| 1537 |
-
"mtp.layers.0.mlp.experts.269.up_proj",
|
| 1538 |
-
"mtp.layers.0.mlp.experts.27.down_proj",
|
| 1539 |
-
"mtp.layers.0.mlp.experts.27.gate_proj",
|
| 1540 |
-
"mtp.layers.0.mlp.experts.27.up_proj",
|
| 1541 |
-
"mtp.layers.0.mlp.experts.270.down_proj",
|
| 1542 |
-
"mtp.layers.0.mlp.experts.270.gate_proj",
|
| 1543 |
-
"mtp.layers.0.mlp.experts.270.up_proj",
|
| 1544 |
-
"mtp.layers.0.mlp.experts.271.down_proj",
|
| 1545 |
-
"mtp.layers.0.mlp.experts.271.gate_proj",
|
| 1546 |
-
"mtp.layers.0.mlp.experts.271.up_proj",
|
| 1547 |
-
"mtp.layers.0.mlp.experts.272.down_proj",
|
| 1548 |
-
"mtp.layers.0.mlp.experts.272.gate_proj",
|
| 1549 |
-
"mtp.layers.0.mlp.experts.272.up_proj",
|
| 1550 |
-
"mtp.layers.0.mlp.experts.273.down_proj",
|
| 1551 |
-
"mtp.layers.0.mlp.experts.273.gate_proj",
|
| 1552 |
-
"mtp.layers.0.mlp.experts.273.up_proj",
|
| 1553 |
-
"mtp.layers.0.mlp.experts.274.down_proj",
|
| 1554 |
-
"mtp.layers.0.mlp.experts.274.gate_proj",
|
| 1555 |
-
"mtp.layers.0.mlp.experts.274.up_proj",
|
| 1556 |
-
"mtp.layers.0.mlp.experts.275.down_proj",
|
| 1557 |
-
"mtp.layers.0.mlp.experts.275.gate_proj",
|
| 1558 |
-
"mtp.layers.0.mlp.experts.275.up_proj",
|
| 1559 |
-
"mtp.layers.0.mlp.experts.276.down_proj",
|
| 1560 |
-
"mtp.layers.0.mlp.experts.276.gate_proj",
|
| 1561 |
-
"mtp.layers.0.mlp.experts.276.up_proj",
|
| 1562 |
-
"mtp.layers.0.mlp.experts.277.down_proj",
|
| 1563 |
-
"mtp.layers.0.mlp.experts.277.gate_proj",
|
| 1564 |
-
"mtp.layers.0.mlp.experts.277.up_proj",
|
| 1565 |
-
"mtp.layers.0.mlp.experts.278.down_proj",
|
| 1566 |
-
"mtp.layers.0.mlp.experts.278.gate_proj",
|
| 1567 |
-
"mtp.layers.0.mlp.experts.278.up_proj",
|
| 1568 |
-
"mtp.layers.0.mlp.experts.279.down_proj",
|
| 1569 |
-
"mtp.layers.0.mlp.experts.279.gate_proj",
|
| 1570 |
-
"mtp.layers.0.mlp.experts.279.up_proj",
|
| 1571 |
-
"mtp.layers.0.mlp.experts.28.down_proj",
|
| 1572 |
-
"mtp.layers.0.mlp.experts.28.gate_proj",
|
| 1573 |
-
"mtp.layers.0.mlp.experts.28.up_proj",
|
| 1574 |
-
"mtp.layers.0.mlp.experts.280.down_proj",
|
| 1575 |
-
"mtp.layers.0.mlp.experts.280.gate_proj",
|
| 1576 |
-
"mtp.layers.0.mlp.experts.280.up_proj",
|
| 1577 |
-
"mtp.layers.0.mlp.experts.281.down_proj",
|
| 1578 |
-
"mtp.layers.0.mlp.experts.281.gate_proj",
|
| 1579 |
-
"mtp.layers.0.mlp.experts.281.up_proj",
|
| 1580 |
-
"mtp.layers.0.mlp.experts.282.down_proj",
|
| 1581 |
-
"mtp.layers.0.mlp.experts.282.gate_proj",
|
| 1582 |
-
"mtp.layers.0.mlp.experts.282.up_proj",
|
| 1583 |
-
"mtp.layers.0.mlp.experts.283.down_proj",
|
| 1584 |
-
"mtp.layers.0.mlp.experts.283.gate_proj",
|
| 1585 |
-
"mtp.layers.0.mlp.experts.283.up_proj",
|
| 1586 |
-
"mtp.layers.0.mlp.experts.284.down_proj",
|
| 1587 |
-
"mtp.layers.0.mlp.experts.284.gate_proj",
|
| 1588 |
-
"mtp.layers.0.mlp.experts.284.up_proj",
|
| 1589 |
-
"mtp.layers.0.mlp.experts.285.down_proj",
|
| 1590 |
-
"mtp.layers.0.mlp.experts.285.gate_proj",
|
| 1591 |
-
"mtp.layers.0.mlp.experts.285.up_proj",
|
| 1592 |
-
"mtp.layers.0.mlp.experts.286.down_proj",
|
| 1593 |
-
"mtp.layers.0.mlp.experts.286.gate_proj",
|
| 1594 |
-
"mtp.layers.0.mlp.experts.286.up_proj",
|
| 1595 |
-
"mtp.layers.0.mlp.experts.287.down_proj",
|
| 1596 |
-
"mtp.layers.0.mlp.experts.287.gate_proj",
|
| 1597 |
-
"mtp.layers.0.mlp.experts.287.up_proj",
|
| 1598 |
-
"mtp.layers.0.mlp.experts.288.down_proj",
|
| 1599 |
-
"mtp.layers.0.mlp.experts.288.gate_proj",
|
| 1600 |
-
"mtp.layers.0.mlp.experts.288.up_proj",
|
| 1601 |
-
"mtp.layers.0.mlp.experts.289.down_proj",
|
| 1602 |
-
"mtp.layers.0.mlp.experts.289.gate_proj",
|
| 1603 |
-
"mtp.layers.0.mlp.experts.289.up_proj",
|
| 1604 |
-
"mtp.layers.0.mlp.experts.29.down_proj",
|
| 1605 |
-
"mtp.layers.0.mlp.experts.29.gate_proj",
|
| 1606 |
-
"mtp.layers.0.mlp.experts.29.up_proj",
|
| 1607 |
-
"mtp.layers.0.mlp.experts.290.down_proj",
|
| 1608 |
-
"mtp.layers.0.mlp.experts.290.gate_proj",
|
| 1609 |
-
"mtp.layers.0.mlp.experts.290.up_proj",
|
| 1610 |
-
"mtp.layers.0.mlp.experts.291.down_proj",
|
| 1611 |
-
"mtp.layers.0.mlp.experts.291.gate_proj",
|
| 1612 |
-
"mtp.layers.0.mlp.experts.291.up_proj",
|
| 1613 |
-
"mtp.layers.0.mlp.experts.292.down_proj",
|
| 1614 |
-
"mtp.layers.0.mlp.experts.292.gate_proj",
|
| 1615 |
-
"mtp.layers.0.mlp.experts.292.up_proj",
|
| 1616 |
-
"mtp.layers.0.mlp.experts.293.down_proj",
|
| 1617 |
-
"mtp.layers.0.mlp.experts.293.gate_proj",
|
| 1618 |
-
"mtp.layers.0.mlp.experts.293.up_proj",
|
| 1619 |
-
"mtp.layers.0.mlp.experts.294.down_proj",
|
| 1620 |
-
"mtp.layers.0.mlp.experts.294.gate_proj",
|
| 1621 |
-
"mtp.layers.0.mlp.experts.294.up_proj",
|
| 1622 |
-
"mtp.layers.0.mlp.experts.295.down_proj",
|
| 1623 |
-
"mtp.layers.0.mlp.experts.295.gate_proj",
|
| 1624 |
-
"mtp.layers.0.mlp.experts.295.up_proj",
|
| 1625 |
-
"mtp.layers.0.mlp.experts.296.down_proj",
|
| 1626 |
-
"mtp.layers.0.mlp.experts.296.gate_proj",
|
| 1627 |
-
"mtp.layers.0.mlp.experts.296.up_proj",
|
| 1628 |
-
"mtp.layers.0.mlp.experts.297.down_proj",
|
| 1629 |
-
"mtp.layers.0.mlp.experts.297.gate_proj",
|
| 1630 |
-
"mtp.layers.0.mlp.experts.297.up_proj",
|
| 1631 |
-
"mtp.layers.0.mlp.experts.298.down_proj",
|
| 1632 |
-
"mtp.layers.0.mlp.experts.298.gate_proj",
|
| 1633 |
-
"mtp.layers.0.mlp.experts.298.up_proj",
|
| 1634 |
-
"mtp.layers.0.mlp.experts.299.down_proj",
|
| 1635 |
-
"mtp.layers.0.mlp.experts.299.gate_proj",
|
| 1636 |
-
"mtp.layers.0.mlp.experts.299.up_proj",
|
| 1637 |
-
"mtp.layers.0.mlp.experts.3.down_proj",
|
| 1638 |
-
"mtp.layers.0.mlp.experts.3.gate_proj",
|
| 1639 |
-
"mtp.layers.0.mlp.experts.3.up_proj",
|
| 1640 |
-
"mtp.layers.0.mlp.experts.30.down_proj",
|
| 1641 |
-
"mtp.layers.0.mlp.experts.30.gate_proj",
|
| 1642 |
-
"mtp.layers.0.mlp.experts.30.up_proj",
|
| 1643 |
-
"mtp.layers.0.mlp.experts.300.down_proj",
|
| 1644 |
-
"mtp.layers.0.mlp.experts.300.gate_proj",
|
| 1645 |
-
"mtp.layers.0.mlp.experts.300.up_proj",
|
| 1646 |
-
"mtp.layers.0.mlp.experts.301.down_proj",
|
| 1647 |
-
"mtp.layers.0.mlp.experts.301.gate_proj",
|
| 1648 |
-
"mtp.layers.0.mlp.experts.301.up_proj",
|
| 1649 |
-
"mtp.layers.0.mlp.experts.302.down_proj",
|
| 1650 |
-
"mtp.layers.0.mlp.experts.302.gate_proj",
|
| 1651 |
-
"mtp.layers.0.mlp.experts.302.up_proj",
|
| 1652 |
-
"mtp.layers.0.mlp.experts.303.down_proj",
|
| 1653 |
-
"mtp.layers.0.mlp.experts.303.gate_proj",
|
| 1654 |
-
"mtp.layers.0.mlp.experts.303.up_proj",
|
| 1655 |
-
"mtp.layers.0.mlp.experts.304.down_proj",
|
| 1656 |
-
"mtp.layers.0.mlp.experts.304.gate_proj",
|
| 1657 |
-
"mtp.layers.0.mlp.experts.304.up_proj",
|
| 1658 |
-
"mtp.layers.0.mlp.experts.305.down_proj",
|
| 1659 |
-
"mtp.layers.0.mlp.experts.305.gate_proj",
|
| 1660 |
-
"mtp.layers.0.mlp.experts.305.up_proj",
|
| 1661 |
-
"mtp.layers.0.mlp.experts.306.down_proj",
|
| 1662 |
-
"mtp.layers.0.mlp.experts.306.gate_proj",
|
| 1663 |
-
"mtp.layers.0.mlp.experts.306.up_proj",
|
| 1664 |
-
"mtp.layers.0.mlp.experts.307.down_proj",
|
| 1665 |
-
"mtp.layers.0.mlp.experts.307.gate_proj",
|
| 1666 |
-
"mtp.layers.0.mlp.experts.307.up_proj",
|
| 1667 |
-
"mtp.layers.0.mlp.experts.308.down_proj",
|
| 1668 |
-
"mtp.layers.0.mlp.experts.308.gate_proj",
|
| 1669 |
-
"mtp.layers.0.mlp.experts.308.up_proj",
|
| 1670 |
-
"mtp.layers.0.mlp.experts.309.down_proj",
|
| 1671 |
-
"mtp.layers.0.mlp.experts.309.gate_proj",
|
| 1672 |
-
"mtp.layers.0.mlp.experts.309.up_proj",
|
| 1673 |
-
"mtp.layers.0.mlp.experts.31.down_proj",
|
| 1674 |
-
"mtp.layers.0.mlp.experts.31.gate_proj",
|
| 1675 |
-
"mtp.layers.0.mlp.experts.31.up_proj",
|
| 1676 |
-
"mtp.layers.0.mlp.experts.310.down_proj",
|
| 1677 |
-
"mtp.layers.0.mlp.experts.310.gate_proj",
|
| 1678 |
-
"mtp.layers.0.mlp.experts.310.up_proj",
|
| 1679 |
-
"mtp.layers.0.mlp.experts.311.down_proj",
|
| 1680 |
-
"mtp.layers.0.mlp.experts.311.gate_proj",
|
| 1681 |
-
"mtp.layers.0.mlp.experts.311.up_proj",
|
| 1682 |
-
"mtp.layers.0.mlp.experts.312.down_proj",
|
| 1683 |
-
"mtp.layers.0.mlp.experts.312.gate_proj",
|
| 1684 |
-
"mtp.layers.0.mlp.experts.312.up_proj",
|
| 1685 |
-
"mtp.layers.0.mlp.experts.313.down_proj",
|
| 1686 |
-
"mtp.layers.0.mlp.experts.313.gate_proj",
|
| 1687 |
-
"mtp.layers.0.mlp.experts.313.up_proj",
|
| 1688 |
-
"mtp.layers.0.mlp.experts.314.down_proj",
|
| 1689 |
-
"mtp.layers.0.mlp.experts.314.gate_proj",
|
| 1690 |
-
"mtp.layers.0.mlp.experts.314.up_proj",
|
| 1691 |
-
"mtp.layers.0.mlp.experts.315.down_proj",
|
| 1692 |
-
"mtp.layers.0.mlp.experts.315.gate_proj",
|
| 1693 |
-
"mtp.layers.0.mlp.experts.315.up_proj",
|
| 1694 |
-
"mtp.layers.0.mlp.experts.316.down_proj",
|
| 1695 |
-
"mtp.layers.0.mlp.experts.316.gate_proj",
|
| 1696 |
-
"mtp.layers.0.mlp.experts.316.up_proj",
|
| 1697 |
-
"mtp.layers.0.mlp.experts.317.down_proj",
|
| 1698 |
-
"mtp.layers.0.mlp.experts.317.gate_proj",
|
| 1699 |
-
"mtp.layers.0.mlp.experts.317.up_proj",
|
| 1700 |
-
"mtp.layers.0.mlp.experts.318.down_proj",
|
| 1701 |
-
"mtp.layers.0.mlp.experts.318.gate_proj",
|
| 1702 |
-
"mtp.layers.0.mlp.experts.318.up_proj",
|
| 1703 |
-
"mtp.layers.0.mlp.experts.319.down_proj",
|
| 1704 |
-
"mtp.layers.0.mlp.experts.319.gate_proj",
|
| 1705 |
-
"mtp.layers.0.mlp.experts.319.up_proj",
|
| 1706 |
-
"mtp.layers.0.mlp.experts.32.down_proj",
|
| 1707 |
-
"mtp.layers.0.mlp.experts.32.gate_proj",
|
| 1708 |
-
"mtp.layers.0.mlp.experts.32.up_proj",
|
| 1709 |
-
"mtp.layers.0.mlp.experts.320.down_proj",
|
| 1710 |
-
"mtp.layers.0.mlp.experts.320.gate_proj",
|
| 1711 |
-
"mtp.layers.0.mlp.experts.320.up_proj",
|
| 1712 |
-
"mtp.layers.0.mlp.experts.321.down_proj",
|
| 1713 |
-
"mtp.layers.0.mlp.experts.321.gate_proj",
|
| 1714 |
-
"mtp.layers.0.mlp.experts.321.up_proj",
|
| 1715 |
-
"mtp.layers.0.mlp.experts.322.down_proj",
|
| 1716 |
-
"mtp.layers.0.mlp.experts.322.gate_proj",
|
| 1717 |
-
"mtp.layers.0.mlp.experts.322.up_proj",
|
| 1718 |
-
"mtp.layers.0.mlp.experts.323.down_proj",
|
| 1719 |
-
"mtp.layers.0.mlp.experts.323.gate_proj",
|
| 1720 |
-
"mtp.layers.0.mlp.experts.323.up_proj",
|
| 1721 |
-
"mtp.layers.0.mlp.experts.324.down_proj",
|
| 1722 |
-
"mtp.layers.0.mlp.experts.324.gate_proj",
|
| 1723 |
-
"mtp.layers.0.mlp.experts.324.up_proj",
|
| 1724 |
-
"mtp.layers.0.mlp.experts.325.down_proj",
|
| 1725 |
-
"mtp.layers.0.mlp.experts.325.gate_proj",
|
| 1726 |
-
"mtp.layers.0.mlp.experts.325.up_proj",
|
| 1727 |
-
"mtp.layers.0.mlp.experts.326.down_proj",
|
| 1728 |
-
"mtp.layers.0.mlp.experts.326.gate_proj",
|
| 1729 |
-
"mtp.layers.0.mlp.experts.326.up_proj",
|
| 1730 |
-
"mtp.layers.0.mlp.experts.327.down_proj",
|
| 1731 |
-
"mtp.layers.0.mlp.experts.327.gate_proj",
|
| 1732 |
-
"mtp.layers.0.mlp.experts.327.up_proj",
|
| 1733 |
-
"mtp.layers.0.mlp.experts.328.down_proj",
|
| 1734 |
-
"mtp.layers.0.mlp.experts.328.gate_proj",
|
| 1735 |
-
"mtp.layers.0.mlp.experts.328.up_proj",
|
| 1736 |
-
"mtp.layers.0.mlp.experts.329.down_proj",
|
| 1737 |
-
"mtp.layers.0.mlp.experts.329.gate_proj",
|
| 1738 |
-
"mtp.layers.0.mlp.experts.329.up_proj",
|
| 1739 |
-
"mtp.layers.0.mlp.experts.33.down_proj",
|
| 1740 |
-
"mtp.layers.0.mlp.experts.33.gate_proj",
|
| 1741 |
-
"mtp.layers.0.mlp.experts.33.up_proj",
|
| 1742 |
-
"mtp.layers.0.mlp.experts.330.down_proj",
|
| 1743 |
-
"mtp.layers.0.mlp.experts.330.gate_proj",
|
| 1744 |
-
"mtp.layers.0.mlp.experts.330.up_proj",
|
| 1745 |
-
"mtp.layers.0.mlp.experts.331.down_proj",
|
| 1746 |
-
"mtp.layers.0.mlp.experts.331.gate_proj",
|
| 1747 |
-
"mtp.layers.0.mlp.experts.331.up_proj",
|
| 1748 |
-
"mtp.layers.0.mlp.experts.332.down_proj",
|
| 1749 |
-
"mtp.layers.0.mlp.experts.332.gate_proj",
|
| 1750 |
-
"mtp.layers.0.mlp.experts.332.up_proj",
|
| 1751 |
-
"mtp.layers.0.mlp.experts.333.down_proj",
|
| 1752 |
-
"mtp.layers.0.mlp.experts.333.gate_proj",
|
| 1753 |
-
"mtp.layers.0.mlp.experts.333.up_proj",
|
| 1754 |
-
"mtp.layers.0.mlp.experts.334.down_proj",
|
| 1755 |
-
"mtp.layers.0.mlp.experts.334.gate_proj",
|
| 1756 |
-
"mtp.layers.0.mlp.experts.334.up_proj",
|
| 1757 |
-
"mtp.layers.0.mlp.experts.335.down_proj",
|
| 1758 |
-
"mtp.layers.0.mlp.experts.335.gate_proj",
|
| 1759 |
-
"mtp.layers.0.mlp.experts.335.up_proj",
|
| 1760 |
-
"mtp.layers.0.mlp.experts.336.down_proj",
|
| 1761 |
-
"mtp.layers.0.mlp.experts.336.gate_proj",
|
| 1762 |
-
"mtp.layers.0.mlp.experts.336.up_proj",
|
| 1763 |
-
"mtp.layers.0.mlp.experts.337.down_proj",
|
| 1764 |
-
"mtp.layers.0.mlp.experts.337.gate_proj",
|
| 1765 |
-
"mtp.layers.0.mlp.experts.337.up_proj",
|
| 1766 |
-
"mtp.layers.0.mlp.experts.338.down_proj",
|
| 1767 |
-
"mtp.layers.0.mlp.experts.338.gate_proj",
|
| 1768 |
-
"mtp.layers.0.mlp.experts.338.up_proj",
|
| 1769 |
-
"mtp.layers.0.mlp.experts.339.down_proj",
|
| 1770 |
-
"mtp.layers.0.mlp.experts.339.gate_proj",
|
| 1771 |
-
"mtp.layers.0.mlp.experts.339.up_proj",
|
| 1772 |
-
"mtp.layers.0.mlp.experts.34.down_proj",
|
| 1773 |
-
"mtp.layers.0.mlp.experts.34.gate_proj",
|
| 1774 |
-
"mtp.layers.0.mlp.experts.34.up_proj",
|
| 1775 |
-
"mtp.layers.0.mlp.experts.340.down_proj",
|
| 1776 |
-
"mtp.layers.0.mlp.experts.340.gate_proj",
|
| 1777 |
-
"mtp.layers.0.mlp.experts.340.up_proj",
|
| 1778 |
-
"mtp.layers.0.mlp.experts.341.down_proj",
|
| 1779 |
-
"mtp.layers.0.mlp.experts.341.gate_proj",
|
| 1780 |
-
"mtp.layers.0.mlp.experts.341.up_proj",
|
| 1781 |
-
"mtp.layers.0.mlp.experts.342.down_proj",
|
| 1782 |
-
"mtp.layers.0.mlp.experts.342.gate_proj",
|
| 1783 |
-
"mtp.layers.0.mlp.experts.342.up_proj",
|
| 1784 |
-
"mtp.layers.0.mlp.experts.343.down_proj",
|
| 1785 |
-
"mtp.layers.0.mlp.experts.343.gate_proj",
|
| 1786 |
-
"mtp.layers.0.mlp.experts.343.up_proj",
|
| 1787 |
-
"mtp.layers.0.mlp.experts.344.down_proj",
|
| 1788 |
-
"mtp.layers.0.mlp.experts.344.gate_proj",
|
| 1789 |
-
"mtp.layers.0.mlp.experts.344.up_proj",
|
| 1790 |
-
"mtp.layers.0.mlp.experts.345.down_proj",
|
| 1791 |
-
"mtp.layers.0.mlp.experts.345.gate_proj",
|
| 1792 |
-
"mtp.layers.0.mlp.experts.345.up_proj",
|
| 1793 |
-
"mtp.layers.0.mlp.experts.346.down_proj",
|
| 1794 |
-
"mtp.layers.0.mlp.experts.346.gate_proj",
|
| 1795 |
-
"mtp.layers.0.mlp.experts.346.up_proj",
|
| 1796 |
-
"mtp.layers.0.mlp.experts.347.down_proj",
|
| 1797 |
-
"mtp.layers.0.mlp.experts.347.gate_proj",
|
| 1798 |
-
"mtp.layers.0.mlp.experts.347.up_proj",
|
| 1799 |
-
"mtp.layers.0.mlp.experts.348.down_proj",
|
| 1800 |
-
"mtp.layers.0.mlp.experts.348.gate_proj",
|
| 1801 |
-
"mtp.layers.0.mlp.experts.348.up_proj",
|
| 1802 |
-
"mtp.layers.0.mlp.experts.349.down_proj",
|
| 1803 |
-
"mtp.layers.0.mlp.experts.349.gate_proj",
|
| 1804 |
-
"mtp.layers.0.mlp.experts.349.up_proj",
|
| 1805 |
-
"mtp.layers.0.mlp.experts.35.down_proj",
|
| 1806 |
-
"mtp.layers.0.mlp.experts.35.gate_proj",
|
| 1807 |
-
"mtp.layers.0.mlp.experts.35.up_proj",
|
| 1808 |
-
"mtp.layers.0.mlp.experts.350.down_proj",
|
| 1809 |
-
"mtp.layers.0.mlp.experts.350.gate_proj",
|
| 1810 |
-
"mtp.layers.0.mlp.experts.350.up_proj",
|
| 1811 |
-
"mtp.layers.0.mlp.experts.351.down_proj",
|
| 1812 |
-
"mtp.layers.0.mlp.experts.351.gate_proj",
|
| 1813 |
-
"mtp.layers.0.mlp.experts.351.up_proj",
|
| 1814 |
-
"mtp.layers.0.mlp.experts.352.down_proj",
|
| 1815 |
-
"mtp.layers.0.mlp.experts.352.gate_proj",
|
| 1816 |
-
"mtp.layers.0.mlp.experts.352.up_proj",
|
| 1817 |
-
"mtp.layers.0.mlp.experts.353.down_proj",
|
| 1818 |
-
"mtp.layers.0.mlp.experts.353.gate_proj",
|
| 1819 |
-
"mtp.layers.0.mlp.experts.353.up_proj",
|
| 1820 |
-
"mtp.layers.0.mlp.experts.354.down_proj",
|
| 1821 |
-
"mtp.layers.0.mlp.experts.354.gate_proj",
|
| 1822 |
-
"mtp.layers.0.mlp.experts.354.up_proj",
|
| 1823 |
-
"mtp.layers.0.mlp.experts.355.down_proj",
|
| 1824 |
-
"mtp.layers.0.mlp.experts.355.gate_proj",
|
| 1825 |
-
"mtp.layers.0.mlp.experts.355.up_proj",
|
| 1826 |
-
"mtp.layers.0.mlp.experts.356.down_proj",
|
| 1827 |
-
"mtp.layers.0.mlp.experts.356.gate_proj",
|
| 1828 |
-
"mtp.layers.0.mlp.experts.356.up_proj",
|
| 1829 |
-
"mtp.layers.0.mlp.experts.357.down_proj",
|
| 1830 |
-
"mtp.layers.0.mlp.experts.357.gate_proj",
|
| 1831 |
-
"mtp.layers.0.mlp.experts.357.up_proj",
|
| 1832 |
-
"mtp.layers.0.mlp.experts.358.down_proj",
|
| 1833 |
-
"mtp.layers.0.mlp.experts.358.gate_proj",
|
| 1834 |
-
"mtp.layers.0.mlp.experts.358.up_proj",
|
| 1835 |
-
"mtp.layers.0.mlp.experts.359.down_proj",
|
| 1836 |
-
"mtp.layers.0.mlp.experts.359.gate_proj",
|
| 1837 |
-
"mtp.layers.0.mlp.experts.359.up_proj",
|
| 1838 |
-
"mtp.layers.0.mlp.experts.36.down_proj",
|
| 1839 |
-
"mtp.layers.0.mlp.experts.36.gate_proj",
|
| 1840 |
-
"mtp.layers.0.mlp.experts.36.up_proj",
|
| 1841 |
-
"mtp.layers.0.mlp.experts.360.down_proj",
|
| 1842 |
-
"mtp.layers.0.mlp.experts.360.gate_proj",
|
| 1843 |
-
"mtp.layers.0.mlp.experts.360.up_proj",
|
| 1844 |
-
"mtp.layers.0.mlp.experts.361.down_proj",
|
| 1845 |
-
"mtp.layers.0.mlp.experts.361.gate_proj",
|
| 1846 |
-
"mtp.layers.0.mlp.experts.361.up_proj",
|
| 1847 |
-
"mtp.layers.0.mlp.experts.362.down_proj",
|
| 1848 |
-
"mtp.layers.0.mlp.experts.362.gate_proj",
|
| 1849 |
-
"mtp.layers.0.mlp.experts.362.up_proj",
|
| 1850 |
-
"mtp.layers.0.mlp.experts.363.down_proj",
|
| 1851 |
-
"mtp.layers.0.mlp.experts.363.gate_proj",
|
| 1852 |
-
"mtp.layers.0.mlp.experts.363.up_proj",
|
| 1853 |
-
"mtp.layers.0.mlp.experts.364.down_proj",
|
| 1854 |
-
"mtp.layers.0.mlp.experts.364.gate_proj",
|
| 1855 |
-
"mtp.layers.0.mlp.experts.364.up_proj",
|
| 1856 |
-
"mtp.layers.0.mlp.experts.365.down_proj",
|
| 1857 |
-
"mtp.layers.0.mlp.experts.365.gate_proj",
|
| 1858 |
-
"mtp.layers.0.mlp.experts.365.up_proj",
|
| 1859 |
-
"mtp.layers.0.mlp.experts.366.down_proj",
|
| 1860 |
-
"mtp.layers.0.mlp.experts.366.gate_proj",
|
| 1861 |
-
"mtp.layers.0.mlp.experts.366.up_proj",
|
| 1862 |
-
"mtp.layers.0.mlp.experts.367.down_proj",
|
| 1863 |
-
"mtp.layers.0.mlp.experts.367.gate_proj",
|
| 1864 |
-
"mtp.layers.0.mlp.experts.367.up_proj",
|
| 1865 |
-
"mtp.layers.0.mlp.experts.368.down_proj",
|
| 1866 |
-
"mtp.layers.0.mlp.experts.368.gate_proj",
|
| 1867 |
-
"mtp.layers.0.mlp.experts.368.up_proj",
|
| 1868 |
-
"mtp.layers.0.mlp.experts.369.down_proj",
|
| 1869 |
-
"mtp.layers.0.mlp.experts.369.gate_proj",
|
| 1870 |
-
"mtp.layers.0.mlp.experts.369.up_proj",
|
| 1871 |
-
"mtp.layers.0.mlp.experts.37.down_proj",
|
| 1872 |
-
"mtp.layers.0.mlp.experts.37.gate_proj",
|
| 1873 |
-
"mtp.layers.0.mlp.experts.37.up_proj",
|
| 1874 |
-
"mtp.layers.0.mlp.experts.370.down_proj",
|
| 1875 |
-
"mtp.layers.0.mlp.experts.370.gate_proj",
|
| 1876 |
-
"mtp.layers.0.mlp.experts.370.up_proj",
|
| 1877 |
-
"mtp.layers.0.mlp.experts.371.down_proj",
|
| 1878 |
-
"mtp.layers.0.mlp.experts.371.gate_proj",
|
| 1879 |
-
"mtp.layers.0.mlp.experts.371.up_proj",
|
| 1880 |
-
"mtp.layers.0.mlp.experts.372.down_proj",
|
| 1881 |
-
"mtp.layers.0.mlp.experts.372.gate_proj",
|
| 1882 |
-
"mtp.layers.0.mlp.experts.372.up_proj",
|
| 1883 |
-
"mtp.layers.0.mlp.experts.373.down_proj",
|
| 1884 |
-
"mtp.layers.0.mlp.experts.373.gate_proj",
|
| 1885 |
-
"mtp.layers.0.mlp.experts.373.up_proj",
|
| 1886 |
-
"mtp.layers.0.mlp.experts.374.down_proj",
|
| 1887 |
-
"mtp.layers.0.mlp.experts.374.gate_proj",
|
| 1888 |
-
"mtp.layers.0.mlp.experts.374.up_proj",
|
| 1889 |
-
"mtp.layers.0.mlp.experts.375.down_proj",
|
| 1890 |
-
"mtp.layers.0.mlp.experts.375.gate_proj",
|
| 1891 |
-
"mtp.layers.0.mlp.experts.375.up_proj",
|
| 1892 |
-
"mtp.layers.0.mlp.experts.376.down_proj",
|
| 1893 |
-
"mtp.layers.0.mlp.experts.376.gate_proj",
|
| 1894 |
-
"mtp.layers.0.mlp.experts.376.up_proj",
|
| 1895 |
-
"mtp.layers.0.mlp.experts.377.down_proj",
|
| 1896 |
-
"mtp.layers.0.mlp.experts.377.gate_proj",
|
| 1897 |
-
"mtp.layers.0.mlp.experts.377.up_proj",
|
| 1898 |
-
"mtp.layers.0.mlp.experts.378.down_proj",
|
| 1899 |
-
"mtp.layers.0.mlp.experts.378.gate_proj",
|
| 1900 |
-
"mtp.layers.0.mlp.experts.378.up_proj",
|
| 1901 |
-
"mtp.layers.0.mlp.experts.379.down_proj",
|
| 1902 |
-
"mtp.layers.0.mlp.experts.379.gate_proj",
|
| 1903 |
-
"mtp.layers.0.mlp.experts.379.up_proj",
|
| 1904 |
-
"mtp.layers.0.mlp.experts.38.down_proj",
|
| 1905 |
-
"mtp.layers.0.mlp.experts.38.gate_proj",
|
| 1906 |
-
"mtp.layers.0.mlp.experts.38.up_proj",
|
| 1907 |
-
"mtp.layers.0.mlp.experts.380.down_proj",
|
| 1908 |
-
"mtp.layers.0.mlp.experts.380.gate_proj",
|
| 1909 |
-
"mtp.layers.0.mlp.experts.380.up_proj",
|
| 1910 |
-
"mtp.layers.0.mlp.experts.381.down_proj",
|
| 1911 |
-
"mtp.layers.0.mlp.experts.381.gate_proj",
|
| 1912 |
-
"mtp.layers.0.mlp.experts.381.up_proj",
|
| 1913 |
-
"mtp.layers.0.mlp.experts.382.down_proj",
|
| 1914 |
-
"mtp.layers.0.mlp.experts.382.gate_proj",
|
| 1915 |
-
"mtp.layers.0.mlp.experts.382.up_proj",
|
| 1916 |
-
"mtp.layers.0.mlp.experts.383.down_proj",
|
| 1917 |
-
"mtp.layers.0.mlp.experts.383.gate_proj",
|
| 1918 |
-
"mtp.layers.0.mlp.experts.383.up_proj",
|
| 1919 |
-
"mtp.layers.0.mlp.experts.384.down_proj",
|
| 1920 |
-
"mtp.layers.0.mlp.experts.384.gate_proj",
|
| 1921 |
-
"mtp.layers.0.mlp.experts.384.up_proj",
|
| 1922 |
-
"mtp.layers.0.mlp.experts.385.down_proj",
|
| 1923 |
-
"mtp.layers.0.mlp.experts.385.gate_proj",
|
| 1924 |
-
"mtp.layers.0.mlp.experts.385.up_proj",
|
| 1925 |
-
"mtp.layers.0.mlp.experts.386.down_proj",
|
| 1926 |
-
"mtp.layers.0.mlp.experts.386.gate_proj",
|
| 1927 |
-
"mtp.layers.0.mlp.experts.386.up_proj",
|
| 1928 |
-
"mtp.layers.0.mlp.experts.387.down_proj",
|
| 1929 |
-
"mtp.layers.0.mlp.experts.387.gate_proj",
|
| 1930 |
-
"mtp.layers.0.mlp.experts.387.up_proj",
|
| 1931 |
-
"mtp.layers.0.mlp.experts.388.down_proj",
|
| 1932 |
-
"mtp.layers.0.mlp.experts.388.gate_proj",
|
| 1933 |
-
"mtp.layers.0.mlp.experts.388.up_proj",
|
| 1934 |
-
"mtp.layers.0.mlp.experts.389.down_proj",
|
| 1935 |
-
"mtp.layers.0.mlp.experts.389.gate_proj",
|
| 1936 |
-
"mtp.layers.0.mlp.experts.389.up_proj",
|
| 1937 |
-
"mtp.layers.0.mlp.experts.39.down_proj",
|
| 1938 |
-
"mtp.layers.0.mlp.experts.39.gate_proj",
|
| 1939 |
-
"mtp.layers.0.mlp.experts.39.up_proj",
|
| 1940 |
-
"mtp.layers.0.mlp.experts.390.down_proj",
|
| 1941 |
-
"mtp.layers.0.mlp.experts.390.gate_proj",
|
| 1942 |
-
"mtp.layers.0.mlp.experts.390.up_proj",
|
| 1943 |
-
"mtp.layers.0.mlp.experts.391.down_proj",
|
| 1944 |
-
"mtp.layers.0.mlp.experts.391.gate_proj",
|
| 1945 |
-
"mtp.layers.0.mlp.experts.391.up_proj",
|
| 1946 |
-
"mtp.layers.0.mlp.experts.392.down_proj",
|
| 1947 |
-
"mtp.layers.0.mlp.experts.392.gate_proj",
|
| 1948 |
-
"mtp.layers.0.mlp.experts.392.up_proj",
|
| 1949 |
-
"mtp.layers.0.mlp.experts.393.down_proj",
|
| 1950 |
-
"mtp.layers.0.mlp.experts.393.gate_proj",
|
| 1951 |
-
"mtp.layers.0.mlp.experts.393.up_proj",
|
| 1952 |
-
"mtp.layers.0.mlp.experts.394.down_proj",
|
| 1953 |
-
"mtp.layers.0.mlp.experts.394.gate_proj",
|
| 1954 |
-
"mtp.layers.0.mlp.experts.394.up_proj",
|
| 1955 |
-
"mtp.layers.0.mlp.experts.395.down_proj",
|
| 1956 |
-
"mtp.layers.0.mlp.experts.395.gate_proj",
|
| 1957 |
-
"mtp.layers.0.mlp.experts.395.up_proj",
|
| 1958 |
-
"mtp.layers.0.mlp.experts.396.down_proj",
|
| 1959 |
-
"mtp.layers.0.mlp.experts.396.gate_proj",
|
| 1960 |
-
"mtp.layers.0.mlp.experts.396.up_proj",
|
| 1961 |
-
"mtp.layers.0.mlp.experts.397.down_proj",
|
| 1962 |
-
"mtp.layers.0.mlp.experts.397.gate_proj",
|
| 1963 |
-
"mtp.layers.0.mlp.experts.397.up_proj",
|
| 1964 |
-
"mtp.layers.0.mlp.experts.398.down_proj",
|
| 1965 |
-
"mtp.layers.0.mlp.experts.398.gate_proj",
|
| 1966 |
-
"mtp.layers.0.mlp.experts.398.up_proj",
|
| 1967 |
-
"mtp.layers.0.mlp.experts.399.down_proj",
|
| 1968 |
-
"mtp.layers.0.mlp.experts.399.gate_proj",
|
| 1969 |
-
"mtp.layers.0.mlp.experts.399.up_proj",
|
| 1970 |
-
"mtp.layers.0.mlp.experts.4.down_proj",
|
| 1971 |
-
"mtp.layers.0.mlp.experts.4.gate_proj",
|
| 1972 |
-
"mtp.layers.0.mlp.experts.4.up_proj",
|
| 1973 |
-
"mtp.layers.0.mlp.experts.40.down_proj",
|
| 1974 |
-
"mtp.layers.0.mlp.experts.40.gate_proj",
|
| 1975 |
-
"mtp.layers.0.mlp.experts.40.up_proj",
|
| 1976 |
-
"mtp.layers.0.mlp.experts.400.down_proj",
|
| 1977 |
-
"mtp.layers.0.mlp.experts.400.gate_proj",
|
| 1978 |
-
"mtp.layers.0.mlp.experts.400.up_proj",
|
| 1979 |
-
"mtp.layers.0.mlp.experts.401.down_proj",
|
| 1980 |
-
"mtp.layers.0.mlp.experts.401.gate_proj",
|
| 1981 |
-
"mtp.layers.0.mlp.experts.401.up_proj",
|
| 1982 |
-
"mtp.layers.0.mlp.experts.402.down_proj",
|
| 1983 |
-
"mtp.layers.0.mlp.experts.402.gate_proj",
|
| 1984 |
-
"mtp.layers.0.mlp.experts.402.up_proj",
|
| 1985 |
-
"mtp.layers.0.mlp.experts.403.down_proj",
|
| 1986 |
-
"mtp.layers.0.mlp.experts.403.gate_proj",
|
| 1987 |
-
"mtp.layers.0.mlp.experts.403.up_proj",
|
| 1988 |
-
"mtp.layers.0.mlp.experts.404.down_proj",
|
| 1989 |
-
"mtp.layers.0.mlp.experts.404.gate_proj",
|
| 1990 |
-
"mtp.layers.0.mlp.experts.404.up_proj",
|
| 1991 |
-
"mtp.layers.0.mlp.experts.405.down_proj",
|
| 1992 |
-
"mtp.layers.0.mlp.experts.405.gate_proj",
|
| 1993 |
-
"mtp.layers.0.mlp.experts.405.up_proj",
|
| 1994 |
-
"mtp.layers.0.mlp.experts.406.down_proj",
|
| 1995 |
-
"mtp.layers.0.mlp.experts.406.gate_proj",
|
| 1996 |
-
"mtp.layers.0.mlp.experts.406.up_proj",
|
| 1997 |
-
"mtp.layers.0.mlp.experts.407.down_proj",
|
| 1998 |
-
"mtp.layers.0.mlp.experts.407.gate_proj",
|
| 1999 |
-
"mtp.layers.0.mlp.experts.407.up_proj",
|
| 2000 |
-
"mtp.layers.0.mlp.experts.408.down_proj",
|
| 2001 |
-
"mtp.layers.0.mlp.experts.408.gate_proj",
|
| 2002 |
-
"mtp.layers.0.mlp.experts.408.up_proj",
|
| 2003 |
-
"mtp.layers.0.mlp.experts.409.down_proj",
|
| 2004 |
-
"mtp.layers.0.mlp.experts.409.gate_proj",
|
| 2005 |
-
"mtp.layers.0.mlp.experts.409.up_proj",
|
| 2006 |
-
"mtp.layers.0.mlp.experts.41.down_proj",
|
| 2007 |
-
"mtp.layers.0.mlp.experts.41.gate_proj",
|
| 2008 |
-
"mtp.layers.0.mlp.experts.41.up_proj",
|
| 2009 |
-
"mtp.layers.0.mlp.experts.410.down_proj",
|
| 2010 |
-
"mtp.layers.0.mlp.experts.410.gate_proj",
|
| 2011 |
-
"mtp.layers.0.mlp.experts.410.up_proj",
|
| 2012 |
-
"mtp.layers.0.mlp.experts.411.down_proj",
|
| 2013 |
-
"mtp.layers.0.mlp.experts.411.gate_proj",
|
| 2014 |
-
"mtp.layers.0.mlp.experts.411.up_proj",
|
| 2015 |
-
"mtp.layers.0.mlp.experts.412.down_proj",
|
| 2016 |
-
"mtp.layers.0.mlp.experts.412.gate_proj",
|
| 2017 |
-
"mtp.layers.0.mlp.experts.412.up_proj",
|
| 2018 |
-
"mtp.layers.0.mlp.experts.413.down_proj",
|
| 2019 |
-
"mtp.layers.0.mlp.experts.413.gate_proj",
|
| 2020 |
-
"mtp.layers.0.mlp.experts.413.up_proj",
|
| 2021 |
-
"mtp.layers.0.mlp.experts.414.down_proj",
|
| 2022 |
-
"mtp.layers.0.mlp.experts.414.gate_proj",
|
| 2023 |
-
"mtp.layers.0.mlp.experts.414.up_proj",
|
| 2024 |
-
"mtp.layers.0.mlp.experts.415.down_proj",
|
| 2025 |
-
"mtp.layers.0.mlp.experts.415.gate_proj",
|
| 2026 |
-
"mtp.layers.0.mlp.experts.415.up_proj",
|
| 2027 |
-
"mtp.layers.0.mlp.experts.416.down_proj",
|
| 2028 |
-
"mtp.layers.0.mlp.experts.416.gate_proj",
|
| 2029 |
-
"mtp.layers.0.mlp.experts.416.up_proj",
|
| 2030 |
-
"mtp.layers.0.mlp.experts.417.down_proj",
|
| 2031 |
-
"mtp.layers.0.mlp.experts.417.gate_proj",
|
| 2032 |
-
"mtp.layers.0.mlp.experts.417.up_proj",
|
| 2033 |
-
"mtp.layers.0.mlp.experts.418.down_proj",
|
| 2034 |
-
"mtp.layers.0.mlp.experts.418.gate_proj",
|
| 2035 |
-
"mtp.layers.0.mlp.experts.418.up_proj",
|
| 2036 |
-
"mtp.layers.0.mlp.experts.419.down_proj",
|
| 2037 |
-
"mtp.layers.0.mlp.experts.419.gate_proj",
|
| 2038 |
-
"mtp.layers.0.mlp.experts.419.up_proj",
|
| 2039 |
-
"mtp.layers.0.mlp.experts.42.down_proj",
|
| 2040 |
-
"mtp.layers.0.mlp.experts.42.gate_proj",
|
| 2041 |
-
"mtp.layers.0.mlp.experts.42.up_proj",
|
| 2042 |
-
"mtp.layers.0.mlp.experts.420.down_proj",
|
| 2043 |
-
"mtp.layers.0.mlp.experts.420.gate_proj",
|
| 2044 |
-
"mtp.layers.0.mlp.experts.420.up_proj",
|
| 2045 |
-
"mtp.layers.0.mlp.experts.421.down_proj",
|
| 2046 |
-
"mtp.layers.0.mlp.experts.421.gate_proj",
|
| 2047 |
-
"mtp.layers.0.mlp.experts.421.up_proj",
|
| 2048 |
-
"mtp.layers.0.mlp.experts.422.down_proj",
|
| 2049 |
-
"mtp.layers.0.mlp.experts.422.gate_proj",
|
| 2050 |
-
"mtp.layers.0.mlp.experts.422.up_proj",
|
| 2051 |
-
"mtp.layers.0.mlp.experts.423.down_proj",
|
| 2052 |
-
"mtp.layers.0.mlp.experts.423.gate_proj",
|
| 2053 |
-
"mtp.layers.0.mlp.experts.423.up_proj",
|
| 2054 |
-
"mtp.layers.0.mlp.experts.424.down_proj",
|
| 2055 |
-
"mtp.layers.0.mlp.experts.424.gate_proj",
|
| 2056 |
-
"mtp.layers.0.mlp.experts.424.up_proj",
|
| 2057 |
-
"mtp.layers.0.mlp.experts.425.down_proj",
|
| 2058 |
-
"mtp.layers.0.mlp.experts.425.gate_proj",
|
| 2059 |
-
"mtp.layers.0.mlp.experts.425.up_proj",
|
| 2060 |
-
"mtp.layers.0.mlp.experts.426.down_proj",
|
| 2061 |
-
"mtp.layers.0.mlp.experts.426.gate_proj",
|
| 2062 |
-
"mtp.layers.0.mlp.experts.426.up_proj",
|
| 2063 |
-
"mtp.layers.0.mlp.experts.427.down_proj",
|
| 2064 |
-
"mtp.layers.0.mlp.experts.427.gate_proj",
|
| 2065 |
-
"mtp.layers.0.mlp.experts.427.up_proj",
|
| 2066 |
-
"mtp.layers.0.mlp.experts.428.down_proj",
|
| 2067 |
-
"mtp.layers.0.mlp.experts.428.gate_proj",
|
| 2068 |
-
"mtp.layers.0.mlp.experts.428.up_proj",
|
| 2069 |
-
"mtp.layers.0.mlp.experts.429.down_proj",
|
| 2070 |
-
"mtp.layers.0.mlp.experts.429.gate_proj",
|
| 2071 |
-
"mtp.layers.0.mlp.experts.429.up_proj",
|
| 2072 |
-
"mtp.layers.0.mlp.experts.43.down_proj",
|
| 2073 |
-
"mtp.layers.0.mlp.experts.43.gate_proj",
|
| 2074 |
-
"mtp.layers.0.mlp.experts.43.up_proj",
|
| 2075 |
-
"mtp.layers.0.mlp.experts.430.down_proj",
|
| 2076 |
-
"mtp.layers.0.mlp.experts.430.gate_proj",
|
| 2077 |
-
"mtp.layers.0.mlp.experts.430.up_proj",
|
| 2078 |
-
"mtp.layers.0.mlp.experts.431.down_proj",
|
| 2079 |
-
"mtp.layers.0.mlp.experts.431.gate_proj",
|
| 2080 |
-
"mtp.layers.0.mlp.experts.431.up_proj",
|
| 2081 |
-
"mtp.layers.0.mlp.experts.432.down_proj",
|
| 2082 |
-
"mtp.layers.0.mlp.experts.432.gate_proj",
|
| 2083 |
-
"mtp.layers.0.mlp.experts.432.up_proj",
|
| 2084 |
-
"mtp.layers.0.mlp.experts.433.down_proj",
|
| 2085 |
-
"mtp.layers.0.mlp.experts.433.gate_proj",
|
| 2086 |
-
"mtp.layers.0.mlp.experts.433.up_proj",
|
| 2087 |
-
"mtp.layers.0.mlp.experts.434.down_proj",
|
| 2088 |
-
"mtp.layers.0.mlp.experts.434.gate_proj",
|
| 2089 |
-
"mtp.layers.0.mlp.experts.434.up_proj",
|
| 2090 |
-
"mtp.layers.0.mlp.experts.435.down_proj",
|
| 2091 |
-
"mtp.layers.0.mlp.experts.435.gate_proj",
|
| 2092 |
-
"mtp.layers.0.mlp.experts.435.up_proj",
|
| 2093 |
-
"mtp.layers.0.mlp.experts.436.down_proj",
|
| 2094 |
-
"mtp.layers.0.mlp.experts.436.gate_proj",
|
| 2095 |
-
"mtp.layers.0.mlp.experts.436.up_proj",
|
| 2096 |
-
"mtp.layers.0.mlp.experts.437.down_proj",
|
| 2097 |
-
"mtp.layers.0.mlp.experts.437.gate_proj",
|
| 2098 |
-
"mtp.layers.0.mlp.experts.437.up_proj",
|
| 2099 |
-
"mtp.layers.0.mlp.experts.438.down_proj",
|
| 2100 |
-
"mtp.layers.0.mlp.experts.438.gate_proj",
|
| 2101 |
-
"mtp.layers.0.mlp.experts.438.up_proj",
|
| 2102 |
-
"mtp.layers.0.mlp.experts.439.down_proj",
|
| 2103 |
-
"mtp.layers.0.mlp.experts.439.gate_proj",
|
| 2104 |
-
"mtp.layers.0.mlp.experts.439.up_proj",
|
| 2105 |
-
"mtp.layers.0.mlp.experts.44.down_proj",
|
| 2106 |
-
"mtp.layers.0.mlp.experts.44.gate_proj",
|
| 2107 |
-
"mtp.layers.0.mlp.experts.44.up_proj",
|
| 2108 |
-
"mtp.layers.0.mlp.experts.440.down_proj",
|
| 2109 |
-
"mtp.layers.0.mlp.experts.440.gate_proj",
|
| 2110 |
-
"mtp.layers.0.mlp.experts.440.up_proj",
|
| 2111 |
-
"mtp.layers.0.mlp.experts.441.down_proj",
|
| 2112 |
-
"mtp.layers.0.mlp.experts.441.gate_proj",
|
| 2113 |
-
"mtp.layers.0.mlp.experts.441.up_proj",
|
| 2114 |
-
"mtp.layers.0.mlp.experts.442.down_proj",
|
| 2115 |
-
"mtp.layers.0.mlp.experts.442.gate_proj",
|
| 2116 |
-
"mtp.layers.0.mlp.experts.442.up_proj",
|
| 2117 |
-
"mtp.layers.0.mlp.experts.443.down_proj",
|
| 2118 |
-
"mtp.layers.0.mlp.experts.443.gate_proj",
|
| 2119 |
-
"mtp.layers.0.mlp.experts.443.up_proj",
|
| 2120 |
-
"mtp.layers.0.mlp.experts.444.down_proj",
|
| 2121 |
-
"mtp.layers.0.mlp.experts.444.gate_proj",
|
| 2122 |
-
"mtp.layers.0.mlp.experts.444.up_proj",
|
| 2123 |
-
"mtp.layers.0.mlp.experts.445.down_proj",
|
| 2124 |
-
"mtp.layers.0.mlp.experts.445.gate_proj",
|
| 2125 |
-
"mtp.layers.0.mlp.experts.445.up_proj",
|
| 2126 |
-
"mtp.layers.0.mlp.experts.446.down_proj",
|
| 2127 |
-
"mtp.layers.0.mlp.experts.446.gate_proj",
|
| 2128 |
-
"mtp.layers.0.mlp.experts.446.up_proj",
|
| 2129 |
-
"mtp.layers.0.mlp.experts.447.down_proj",
|
| 2130 |
-
"mtp.layers.0.mlp.experts.447.gate_proj",
|
| 2131 |
-
"mtp.layers.0.mlp.experts.447.up_proj",
|
| 2132 |
-
"mtp.layers.0.mlp.experts.448.down_proj",
|
| 2133 |
-
"mtp.layers.0.mlp.experts.448.gate_proj",
|
| 2134 |
-
"mtp.layers.0.mlp.experts.448.up_proj",
|
| 2135 |
-
"mtp.layers.0.mlp.experts.449.down_proj",
|
| 2136 |
-
"mtp.layers.0.mlp.experts.449.gate_proj",
|
| 2137 |
-
"mtp.layers.0.mlp.experts.449.up_proj",
|
| 2138 |
-
"mtp.layers.0.mlp.experts.45.down_proj",
|
| 2139 |
-
"mtp.layers.0.mlp.experts.45.gate_proj",
|
| 2140 |
-
"mtp.layers.0.mlp.experts.45.up_proj",
|
| 2141 |
-
"mtp.layers.0.mlp.experts.450.down_proj",
|
| 2142 |
-
"mtp.layers.0.mlp.experts.450.gate_proj",
|
| 2143 |
-
"mtp.layers.0.mlp.experts.450.up_proj",
|
| 2144 |
-
"mtp.layers.0.mlp.experts.451.down_proj",
|
| 2145 |
-
"mtp.layers.0.mlp.experts.451.gate_proj",
|
| 2146 |
-
"mtp.layers.0.mlp.experts.451.up_proj",
|
| 2147 |
-
"mtp.layers.0.mlp.experts.452.down_proj",
|
| 2148 |
-
"mtp.layers.0.mlp.experts.452.gate_proj",
|
| 2149 |
-
"mtp.layers.0.mlp.experts.452.up_proj",
|
| 2150 |
-
"mtp.layers.0.mlp.experts.453.down_proj",
|
| 2151 |
-
"mtp.layers.0.mlp.experts.453.gate_proj",
|
| 2152 |
-
"mtp.layers.0.mlp.experts.453.up_proj",
|
| 2153 |
-
"mtp.layers.0.mlp.experts.454.down_proj",
|
| 2154 |
-
"mtp.layers.0.mlp.experts.454.gate_proj",
|
| 2155 |
-
"mtp.layers.0.mlp.experts.454.up_proj",
|
| 2156 |
-
"mtp.layers.0.mlp.experts.455.down_proj",
|
| 2157 |
-
"mtp.layers.0.mlp.experts.455.gate_proj",
|
| 2158 |
-
"mtp.layers.0.mlp.experts.455.up_proj",
|
| 2159 |
-
"mtp.layers.0.mlp.experts.456.down_proj",
|
| 2160 |
-
"mtp.layers.0.mlp.experts.456.gate_proj",
|
| 2161 |
-
"mtp.layers.0.mlp.experts.456.up_proj",
|
| 2162 |
-
"mtp.layers.0.mlp.experts.457.down_proj",
|
| 2163 |
-
"mtp.layers.0.mlp.experts.457.gate_proj",
|
| 2164 |
-
"mtp.layers.0.mlp.experts.457.up_proj",
|
| 2165 |
-
"mtp.layers.0.mlp.experts.458.down_proj",
|
| 2166 |
-
"mtp.layers.0.mlp.experts.458.gate_proj",
|
| 2167 |
-
"mtp.layers.0.mlp.experts.458.up_proj",
|
| 2168 |
-
"mtp.layers.0.mlp.experts.459.down_proj",
|
| 2169 |
-
"mtp.layers.0.mlp.experts.459.gate_proj",
|
| 2170 |
-
"mtp.layers.0.mlp.experts.459.up_proj",
|
| 2171 |
-
"mtp.layers.0.mlp.experts.46.down_proj",
|
| 2172 |
-
"mtp.layers.0.mlp.experts.46.gate_proj",
|
| 2173 |
-
"mtp.layers.0.mlp.experts.46.up_proj",
|
| 2174 |
-
"mtp.layers.0.mlp.experts.460.down_proj",
|
| 2175 |
-
"mtp.layers.0.mlp.experts.460.gate_proj",
|
| 2176 |
-
"mtp.layers.0.mlp.experts.460.up_proj",
|
| 2177 |
-
"mtp.layers.0.mlp.experts.461.down_proj",
|
| 2178 |
-
"mtp.layers.0.mlp.experts.461.gate_proj",
|
| 2179 |
-
"mtp.layers.0.mlp.experts.461.up_proj",
|
| 2180 |
-
"mtp.layers.0.mlp.experts.462.down_proj",
|
| 2181 |
-
"mtp.layers.0.mlp.experts.462.gate_proj",
|
| 2182 |
-
"mtp.layers.0.mlp.experts.462.up_proj",
|
| 2183 |
-
"mtp.layers.0.mlp.experts.463.down_proj",
|
| 2184 |
-
"mtp.layers.0.mlp.experts.463.gate_proj",
|
| 2185 |
-
"mtp.layers.0.mlp.experts.463.up_proj",
|
| 2186 |
-
"mtp.layers.0.mlp.experts.464.down_proj",
|
| 2187 |
-
"mtp.layers.0.mlp.experts.464.gate_proj",
|
| 2188 |
-
"mtp.layers.0.mlp.experts.464.up_proj",
|
| 2189 |
-
"mtp.layers.0.mlp.experts.465.down_proj",
|
| 2190 |
-
"mtp.layers.0.mlp.experts.465.gate_proj",
|
| 2191 |
-
"mtp.layers.0.mlp.experts.465.up_proj",
|
| 2192 |
-
"mtp.layers.0.mlp.experts.466.down_proj",
|
| 2193 |
-
"mtp.layers.0.mlp.experts.466.gate_proj",
|
| 2194 |
-
"mtp.layers.0.mlp.experts.466.up_proj",
|
| 2195 |
-
"mtp.layers.0.mlp.experts.467.down_proj",
|
| 2196 |
-
"mtp.layers.0.mlp.experts.467.gate_proj",
|
| 2197 |
-
"mtp.layers.0.mlp.experts.467.up_proj",
|
| 2198 |
-
"mtp.layers.0.mlp.experts.468.down_proj",
|
| 2199 |
-
"mtp.layers.0.mlp.experts.468.gate_proj",
|
| 2200 |
-
"mtp.layers.0.mlp.experts.468.up_proj",
|
| 2201 |
-
"mtp.layers.0.mlp.experts.469.down_proj",
|
| 2202 |
-
"mtp.layers.0.mlp.experts.469.gate_proj",
|
| 2203 |
-
"mtp.layers.0.mlp.experts.469.up_proj",
|
| 2204 |
-
"mtp.layers.0.mlp.experts.47.down_proj",
|
| 2205 |
-
"mtp.layers.0.mlp.experts.47.gate_proj",
|
| 2206 |
-
"mtp.layers.0.mlp.experts.47.up_proj",
|
| 2207 |
-
"mtp.layers.0.mlp.experts.470.down_proj",
|
| 2208 |
-
"mtp.layers.0.mlp.experts.470.gate_proj",
|
| 2209 |
-
"mtp.layers.0.mlp.experts.470.up_proj",
|
| 2210 |
-
"mtp.layers.0.mlp.experts.471.down_proj",
|
| 2211 |
-
"mtp.layers.0.mlp.experts.471.gate_proj",
|
| 2212 |
-
"mtp.layers.0.mlp.experts.471.up_proj",
|
| 2213 |
-
"mtp.layers.0.mlp.experts.472.down_proj",
|
| 2214 |
-
"mtp.layers.0.mlp.experts.472.gate_proj",
|
| 2215 |
-
"mtp.layers.0.mlp.experts.472.up_proj",
|
| 2216 |
-
"mtp.layers.0.mlp.experts.473.down_proj",
|
| 2217 |
-
"mtp.layers.0.mlp.experts.473.gate_proj",
|
| 2218 |
-
"mtp.layers.0.mlp.experts.473.up_proj",
|
| 2219 |
-
"mtp.layers.0.mlp.experts.474.down_proj",
|
| 2220 |
-
"mtp.layers.0.mlp.experts.474.gate_proj",
|
| 2221 |
-
"mtp.layers.0.mlp.experts.474.up_proj",
|
| 2222 |
-
"mtp.layers.0.mlp.experts.475.down_proj",
|
| 2223 |
-
"mtp.layers.0.mlp.experts.475.gate_proj",
|
| 2224 |
-
"mtp.layers.0.mlp.experts.475.up_proj",
|
| 2225 |
-
"mtp.layers.0.mlp.experts.476.down_proj",
|
| 2226 |
-
"mtp.layers.0.mlp.experts.476.gate_proj",
|
| 2227 |
-
"mtp.layers.0.mlp.experts.476.up_proj",
|
| 2228 |
-
"mtp.layers.0.mlp.experts.477.down_proj",
|
| 2229 |
-
"mtp.layers.0.mlp.experts.477.gate_proj",
|
| 2230 |
-
"mtp.layers.0.mlp.experts.477.up_proj",
|
| 2231 |
-
"mtp.layers.0.mlp.experts.478.down_proj",
|
| 2232 |
-
"mtp.layers.0.mlp.experts.478.gate_proj",
|
| 2233 |
-
"mtp.layers.0.mlp.experts.478.up_proj",
|
| 2234 |
-
"mtp.layers.0.mlp.experts.479.down_proj",
|
| 2235 |
-
"mtp.layers.0.mlp.experts.479.gate_proj",
|
| 2236 |
-
"mtp.layers.0.mlp.experts.479.up_proj",
|
| 2237 |
-
"mtp.layers.0.mlp.experts.48.down_proj",
|
| 2238 |
-
"mtp.layers.0.mlp.experts.48.gate_proj",
|
| 2239 |
-
"mtp.layers.0.mlp.experts.48.up_proj",
|
| 2240 |
-
"mtp.layers.0.mlp.experts.480.down_proj",
|
| 2241 |
-
"mtp.layers.0.mlp.experts.480.gate_proj",
|
| 2242 |
-
"mtp.layers.0.mlp.experts.480.up_proj",
|
| 2243 |
-
"mtp.layers.0.mlp.experts.481.down_proj",
|
| 2244 |
-
"mtp.layers.0.mlp.experts.481.gate_proj",
|
| 2245 |
-
"mtp.layers.0.mlp.experts.481.up_proj",
|
| 2246 |
-
"mtp.layers.0.mlp.experts.482.down_proj",
|
| 2247 |
-
"mtp.layers.0.mlp.experts.482.gate_proj",
|
| 2248 |
-
"mtp.layers.0.mlp.experts.482.up_proj",
|
| 2249 |
-
"mtp.layers.0.mlp.experts.483.down_proj",
|
| 2250 |
-
"mtp.layers.0.mlp.experts.483.gate_proj",
|
| 2251 |
-
"mtp.layers.0.mlp.experts.483.up_proj",
|
| 2252 |
-
"mtp.layers.0.mlp.experts.484.down_proj",
|
| 2253 |
-
"mtp.layers.0.mlp.experts.484.gate_proj",
|
| 2254 |
-
"mtp.layers.0.mlp.experts.484.up_proj",
|
| 2255 |
-
"mtp.layers.0.mlp.experts.485.down_proj",
|
| 2256 |
-
"mtp.layers.0.mlp.experts.485.gate_proj",
|
| 2257 |
-
"mtp.layers.0.mlp.experts.485.up_proj",
|
| 2258 |
-
"mtp.layers.0.mlp.experts.486.down_proj",
|
| 2259 |
-
"mtp.layers.0.mlp.experts.486.gate_proj",
|
| 2260 |
-
"mtp.layers.0.mlp.experts.486.up_proj",
|
| 2261 |
-
"mtp.layers.0.mlp.experts.487.down_proj",
|
| 2262 |
-
"mtp.layers.0.mlp.experts.487.gate_proj",
|
| 2263 |
-
"mtp.layers.0.mlp.experts.487.up_proj",
|
| 2264 |
-
"mtp.layers.0.mlp.experts.488.down_proj",
|
| 2265 |
-
"mtp.layers.0.mlp.experts.488.gate_proj",
|
| 2266 |
-
"mtp.layers.0.mlp.experts.488.up_proj",
|
| 2267 |
-
"mtp.layers.0.mlp.experts.489.down_proj",
|
| 2268 |
-
"mtp.layers.0.mlp.experts.489.gate_proj",
|
| 2269 |
-
"mtp.layers.0.mlp.experts.489.up_proj",
|
| 2270 |
-
"mtp.layers.0.mlp.experts.49.down_proj",
|
| 2271 |
-
"mtp.layers.0.mlp.experts.49.gate_proj",
|
| 2272 |
-
"mtp.layers.0.mlp.experts.49.up_proj",
|
| 2273 |
-
"mtp.layers.0.mlp.experts.490.down_proj",
|
| 2274 |
-
"mtp.layers.0.mlp.experts.490.gate_proj",
|
| 2275 |
-
"mtp.layers.0.mlp.experts.490.up_proj",
|
| 2276 |
-
"mtp.layers.0.mlp.experts.491.down_proj",
|
| 2277 |
-
"mtp.layers.0.mlp.experts.491.gate_proj",
|
| 2278 |
-
"mtp.layers.0.mlp.experts.491.up_proj",
|
| 2279 |
-
"mtp.layers.0.mlp.experts.492.down_proj",
|
| 2280 |
-
"mtp.layers.0.mlp.experts.492.gate_proj",
|
| 2281 |
-
"mtp.layers.0.mlp.experts.492.up_proj",
|
| 2282 |
-
"mtp.layers.0.mlp.experts.493.down_proj",
|
| 2283 |
-
"mtp.layers.0.mlp.experts.493.gate_proj",
|
| 2284 |
-
"mtp.layers.0.mlp.experts.493.up_proj",
|
| 2285 |
-
"mtp.layers.0.mlp.experts.494.down_proj",
|
| 2286 |
-
"mtp.layers.0.mlp.experts.494.gate_proj",
|
| 2287 |
-
"mtp.layers.0.mlp.experts.494.up_proj",
|
| 2288 |
-
"mtp.layers.0.mlp.experts.495.down_proj",
|
| 2289 |
-
"mtp.layers.0.mlp.experts.495.gate_proj",
|
| 2290 |
-
"mtp.layers.0.mlp.experts.495.up_proj",
|
| 2291 |
-
"mtp.layers.0.mlp.experts.496.down_proj",
|
| 2292 |
-
"mtp.layers.0.mlp.experts.496.gate_proj",
|
| 2293 |
-
"mtp.layers.0.mlp.experts.496.up_proj",
|
| 2294 |
-
"mtp.layers.0.mlp.experts.497.down_proj",
|
| 2295 |
-
"mtp.layers.0.mlp.experts.497.gate_proj",
|
| 2296 |
-
"mtp.layers.0.mlp.experts.497.up_proj",
|
| 2297 |
-
"mtp.layers.0.mlp.experts.498.down_proj",
|
| 2298 |
-
"mtp.layers.0.mlp.experts.498.gate_proj",
|
| 2299 |
-
"mtp.layers.0.mlp.experts.498.up_proj",
|
| 2300 |
-
"mtp.layers.0.mlp.experts.499.down_proj",
|
| 2301 |
-
"mtp.layers.0.mlp.experts.499.gate_proj",
|
| 2302 |
-
"mtp.layers.0.mlp.experts.499.up_proj",
|
| 2303 |
-
"mtp.layers.0.mlp.experts.5.down_proj",
|
| 2304 |
-
"mtp.layers.0.mlp.experts.5.gate_proj",
|
| 2305 |
-
"mtp.layers.0.mlp.experts.5.up_proj",
|
| 2306 |
-
"mtp.layers.0.mlp.experts.50.down_proj",
|
| 2307 |
-
"mtp.layers.0.mlp.experts.50.gate_proj",
|
| 2308 |
-
"mtp.layers.0.mlp.experts.50.up_proj",
|
| 2309 |
-
"mtp.layers.0.mlp.experts.500.down_proj",
|
| 2310 |
-
"mtp.layers.0.mlp.experts.500.gate_proj",
|
| 2311 |
-
"mtp.layers.0.mlp.experts.500.up_proj",
|
| 2312 |
-
"mtp.layers.0.mlp.experts.501.down_proj",
|
| 2313 |
-
"mtp.layers.0.mlp.experts.501.gate_proj",
|
| 2314 |
-
"mtp.layers.0.mlp.experts.501.up_proj",
|
| 2315 |
-
"mtp.layers.0.mlp.experts.502.down_proj",
|
| 2316 |
-
"mtp.layers.0.mlp.experts.502.gate_proj",
|
| 2317 |
-
"mtp.layers.0.mlp.experts.502.up_proj",
|
| 2318 |
-
"mtp.layers.0.mlp.experts.503.down_proj",
|
| 2319 |
-
"mtp.layers.0.mlp.experts.503.gate_proj",
|
| 2320 |
-
"mtp.layers.0.mlp.experts.503.up_proj",
|
| 2321 |
-
"mtp.layers.0.mlp.experts.504.down_proj",
|
| 2322 |
-
"mtp.layers.0.mlp.experts.504.gate_proj",
|
| 2323 |
-
"mtp.layers.0.mlp.experts.504.up_proj",
|
| 2324 |
-
"mtp.layers.0.mlp.experts.505.down_proj",
|
| 2325 |
-
"mtp.layers.0.mlp.experts.505.gate_proj",
|
| 2326 |
-
"mtp.layers.0.mlp.experts.505.up_proj",
|
| 2327 |
-
"mtp.layers.0.mlp.experts.506.down_proj",
|
| 2328 |
-
"mtp.layers.0.mlp.experts.506.gate_proj",
|
| 2329 |
-
"mtp.layers.0.mlp.experts.506.up_proj",
|
| 2330 |
-
"mtp.layers.0.mlp.experts.507.down_proj",
|
| 2331 |
-
"mtp.layers.0.mlp.experts.507.gate_proj",
|
| 2332 |
-
"mtp.layers.0.mlp.experts.507.up_proj",
|
| 2333 |
-
"mtp.layers.0.mlp.experts.508.down_proj",
|
| 2334 |
-
"mtp.layers.0.mlp.experts.508.gate_proj",
|
| 2335 |
-
"mtp.layers.0.mlp.experts.508.up_proj",
|
| 2336 |
-
"mtp.layers.0.mlp.experts.509.down_proj",
|
| 2337 |
-
"mtp.layers.0.mlp.experts.509.gate_proj",
|
| 2338 |
-
"mtp.layers.0.mlp.experts.509.up_proj",
|
| 2339 |
-
"mtp.layers.0.mlp.experts.51.down_proj",
|
| 2340 |
-
"mtp.layers.0.mlp.experts.51.gate_proj",
|
| 2341 |
-
"mtp.layers.0.mlp.experts.51.up_proj",
|
| 2342 |
-
"mtp.layers.0.mlp.experts.510.down_proj",
|
| 2343 |
-
"mtp.layers.0.mlp.experts.510.gate_proj",
|
| 2344 |
-
"mtp.layers.0.mlp.experts.510.up_proj",
|
| 2345 |
-
"mtp.layers.0.mlp.experts.511.down_proj",
|
| 2346 |
-
"mtp.layers.0.mlp.experts.511.gate_proj",
|
| 2347 |
-
"mtp.layers.0.mlp.experts.511.up_proj",
|
| 2348 |
-
"mtp.layers.0.mlp.experts.52.down_proj",
|
| 2349 |
-
"mtp.layers.0.mlp.experts.52.gate_proj",
|
| 2350 |
-
"mtp.layers.0.mlp.experts.52.up_proj",
|
| 2351 |
-
"mtp.layers.0.mlp.experts.53.down_proj",
|
| 2352 |
-
"mtp.layers.0.mlp.experts.53.gate_proj",
|
| 2353 |
-
"mtp.layers.0.mlp.experts.53.up_proj",
|
| 2354 |
-
"mtp.layers.0.mlp.experts.54.down_proj",
|
| 2355 |
-
"mtp.layers.0.mlp.experts.54.gate_proj",
|
| 2356 |
-
"mtp.layers.0.mlp.experts.54.up_proj",
|
| 2357 |
-
"mtp.layers.0.mlp.experts.55.down_proj",
|
| 2358 |
-
"mtp.layers.0.mlp.experts.55.gate_proj",
|
| 2359 |
-
"mtp.layers.0.mlp.experts.55.up_proj",
|
| 2360 |
-
"mtp.layers.0.mlp.experts.56.down_proj",
|
| 2361 |
-
"mtp.layers.0.mlp.experts.56.gate_proj",
|
| 2362 |
-
"mtp.layers.0.mlp.experts.56.up_proj",
|
| 2363 |
-
"mtp.layers.0.mlp.experts.57.down_proj",
|
| 2364 |
-
"mtp.layers.0.mlp.experts.57.gate_proj",
|
| 2365 |
-
"mtp.layers.0.mlp.experts.57.up_proj",
|
| 2366 |
-
"mtp.layers.0.mlp.experts.58.down_proj",
|
| 2367 |
-
"mtp.layers.0.mlp.experts.58.gate_proj",
|
| 2368 |
-
"mtp.layers.0.mlp.experts.58.up_proj",
|
| 2369 |
-
"mtp.layers.0.mlp.experts.59.down_proj",
|
| 2370 |
-
"mtp.layers.0.mlp.experts.59.gate_proj",
|
| 2371 |
-
"mtp.layers.0.mlp.experts.59.up_proj",
|
| 2372 |
-
"mtp.layers.0.mlp.experts.6.down_proj",
|
| 2373 |
-
"mtp.layers.0.mlp.experts.6.gate_proj",
|
| 2374 |
-
"mtp.layers.0.mlp.experts.6.up_proj",
|
| 2375 |
-
"mtp.layers.0.mlp.experts.60.down_proj",
|
| 2376 |
-
"mtp.layers.0.mlp.experts.60.gate_proj",
|
| 2377 |
-
"mtp.layers.0.mlp.experts.60.up_proj",
|
| 2378 |
-
"mtp.layers.0.mlp.experts.61.down_proj",
|
| 2379 |
-
"mtp.layers.0.mlp.experts.61.gate_proj",
|
| 2380 |
-
"mtp.layers.0.mlp.experts.61.up_proj",
|
| 2381 |
-
"mtp.layers.0.mlp.experts.62.down_proj",
|
| 2382 |
-
"mtp.layers.0.mlp.experts.62.gate_proj",
|
| 2383 |
-
"mtp.layers.0.mlp.experts.62.up_proj",
|
| 2384 |
-
"mtp.layers.0.mlp.experts.63.down_proj",
|
| 2385 |
-
"mtp.layers.0.mlp.experts.63.gate_proj",
|
| 2386 |
-
"mtp.layers.0.mlp.experts.63.up_proj",
|
| 2387 |
-
"mtp.layers.0.mlp.experts.64.down_proj",
|
| 2388 |
-
"mtp.layers.0.mlp.experts.64.gate_proj",
|
| 2389 |
-
"mtp.layers.0.mlp.experts.64.up_proj",
|
| 2390 |
-
"mtp.layers.0.mlp.experts.65.down_proj",
|
| 2391 |
-
"mtp.layers.0.mlp.experts.65.gate_proj",
|
| 2392 |
-
"mtp.layers.0.mlp.experts.65.up_proj",
|
| 2393 |
-
"mtp.layers.0.mlp.experts.66.down_proj",
|
| 2394 |
-
"mtp.layers.0.mlp.experts.66.gate_proj",
|
| 2395 |
-
"mtp.layers.0.mlp.experts.66.up_proj",
|
| 2396 |
-
"mtp.layers.0.mlp.experts.67.down_proj",
|
| 2397 |
-
"mtp.layers.0.mlp.experts.67.gate_proj",
|
| 2398 |
-
"mtp.layers.0.mlp.experts.67.up_proj",
|
| 2399 |
-
"mtp.layers.0.mlp.experts.68.down_proj",
|
| 2400 |
-
"mtp.layers.0.mlp.experts.68.gate_proj",
|
| 2401 |
-
"mtp.layers.0.mlp.experts.68.up_proj",
|
| 2402 |
-
"mtp.layers.0.mlp.experts.69.down_proj",
|
| 2403 |
-
"mtp.layers.0.mlp.experts.69.gate_proj",
|
| 2404 |
-
"mtp.layers.0.mlp.experts.69.up_proj",
|
| 2405 |
-
"mtp.layers.0.mlp.experts.7.down_proj",
|
| 2406 |
-
"mtp.layers.0.mlp.experts.7.gate_proj",
|
| 2407 |
-
"mtp.layers.0.mlp.experts.7.up_proj",
|
| 2408 |
-
"mtp.layers.0.mlp.experts.70.down_proj",
|
| 2409 |
-
"mtp.layers.0.mlp.experts.70.gate_proj",
|
| 2410 |
-
"mtp.layers.0.mlp.experts.70.up_proj",
|
| 2411 |
-
"mtp.layers.0.mlp.experts.71.down_proj",
|
| 2412 |
-
"mtp.layers.0.mlp.experts.71.gate_proj",
|
| 2413 |
-
"mtp.layers.0.mlp.experts.71.up_proj",
|
| 2414 |
-
"mtp.layers.0.mlp.experts.72.down_proj",
|
| 2415 |
-
"mtp.layers.0.mlp.experts.72.gate_proj",
|
| 2416 |
-
"mtp.layers.0.mlp.experts.72.up_proj",
|
| 2417 |
-
"mtp.layers.0.mlp.experts.73.down_proj",
|
| 2418 |
-
"mtp.layers.0.mlp.experts.73.gate_proj",
|
| 2419 |
-
"mtp.layers.0.mlp.experts.73.up_proj",
|
| 2420 |
-
"mtp.layers.0.mlp.experts.74.down_proj",
|
| 2421 |
-
"mtp.layers.0.mlp.experts.74.gate_proj",
|
| 2422 |
-
"mtp.layers.0.mlp.experts.74.up_proj",
|
| 2423 |
-
"mtp.layers.0.mlp.experts.75.down_proj",
|
| 2424 |
-
"mtp.layers.0.mlp.experts.75.gate_proj",
|
| 2425 |
-
"mtp.layers.0.mlp.experts.75.up_proj",
|
| 2426 |
-
"mtp.layers.0.mlp.experts.76.down_proj",
|
| 2427 |
-
"mtp.layers.0.mlp.experts.76.gate_proj",
|
| 2428 |
-
"mtp.layers.0.mlp.experts.76.up_proj",
|
| 2429 |
-
"mtp.layers.0.mlp.experts.77.down_proj",
|
| 2430 |
-
"mtp.layers.0.mlp.experts.77.gate_proj",
|
| 2431 |
-
"mtp.layers.0.mlp.experts.77.up_proj",
|
| 2432 |
-
"mtp.layers.0.mlp.experts.78.down_proj",
|
| 2433 |
-
"mtp.layers.0.mlp.experts.78.gate_proj",
|
| 2434 |
-
"mtp.layers.0.mlp.experts.78.up_proj",
|
| 2435 |
-
"mtp.layers.0.mlp.experts.79.down_proj",
|
| 2436 |
-
"mtp.layers.0.mlp.experts.79.gate_proj",
|
| 2437 |
-
"mtp.layers.0.mlp.experts.79.up_proj",
|
| 2438 |
-
"mtp.layers.0.mlp.experts.8.down_proj",
|
| 2439 |
-
"mtp.layers.0.mlp.experts.8.gate_proj",
|
| 2440 |
-
"mtp.layers.0.mlp.experts.8.up_proj",
|
| 2441 |
-
"mtp.layers.0.mlp.experts.80.down_proj",
|
| 2442 |
-
"mtp.layers.0.mlp.experts.80.gate_proj",
|
| 2443 |
-
"mtp.layers.0.mlp.experts.80.up_proj",
|
| 2444 |
-
"mtp.layers.0.mlp.experts.81.down_proj",
|
| 2445 |
-
"mtp.layers.0.mlp.experts.81.gate_proj",
|
| 2446 |
-
"mtp.layers.0.mlp.experts.81.up_proj",
|
| 2447 |
-
"mtp.layers.0.mlp.experts.82.down_proj",
|
| 2448 |
-
"mtp.layers.0.mlp.experts.82.gate_proj",
|
| 2449 |
-
"mtp.layers.0.mlp.experts.82.up_proj",
|
| 2450 |
-
"mtp.layers.0.mlp.experts.83.down_proj",
|
| 2451 |
-
"mtp.layers.0.mlp.experts.83.gate_proj",
|
| 2452 |
-
"mtp.layers.0.mlp.experts.83.up_proj",
|
| 2453 |
-
"mtp.layers.0.mlp.experts.84.down_proj",
|
| 2454 |
-
"mtp.layers.0.mlp.experts.84.gate_proj",
|
| 2455 |
-
"mtp.layers.0.mlp.experts.84.up_proj",
|
| 2456 |
-
"mtp.layers.0.mlp.experts.85.down_proj",
|
| 2457 |
-
"mtp.layers.0.mlp.experts.85.gate_proj",
|
| 2458 |
-
"mtp.layers.0.mlp.experts.85.up_proj",
|
| 2459 |
-
"mtp.layers.0.mlp.experts.86.down_proj",
|
| 2460 |
-
"mtp.layers.0.mlp.experts.86.gate_proj",
|
| 2461 |
-
"mtp.layers.0.mlp.experts.86.up_proj",
|
| 2462 |
-
"mtp.layers.0.mlp.experts.87.down_proj",
|
| 2463 |
-
"mtp.layers.0.mlp.experts.87.gate_proj",
|
| 2464 |
-
"mtp.layers.0.mlp.experts.87.up_proj",
|
| 2465 |
-
"mtp.layers.0.mlp.experts.88.down_proj",
|
| 2466 |
-
"mtp.layers.0.mlp.experts.88.gate_proj",
|
| 2467 |
-
"mtp.layers.0.mlp.experts.88.up_proj",
|
| 2468 |
-
"mtp.layers.0.mlp.experts.89.down_proj",
|
| 2469 |
-
"mtp.layers.0.mlp.experts.89.gate_proj",
|
| 2470 |
-
"mtp.layers.0.mlp.experts.89.up_proj",
|
| 2471 |
-
"mtp.layers.0.mlp.experts.9.down_proj",
|
| 2472 |
-
"mtp.layers.0.mlp.experts.9.gate_proj",
|
| 2473 |
-
"mtp.layers.0.mlp.experts.9.up_proj",
|
| 2474 |
-
"mtp.layers.0.mlp.experts.90.down_proj",
|
| 2475 |
-
"mtp.layers.0.mlp.experts.90.gate_proj",
|
| 2476 |
-
"mtp.layers.0.mlp.experts.90.up_proj",
|
| 2477 |
-
"mtp.layers.0.mlp.experts.91.down_proj",
|
| 2478 |
-
"mtp.layers.0.mlp.experts.91.gate_proj",
|
| 2479 |
-
"mtp.layers.0.mlp.experts.91.up_proj",
|
| 2480 |
-
"mtp.layers.0.mlp.experts.92.down_proj",
|
| 2481 |
-
"mtp.layers.0.mlp.experts.92.gate_proj",
|
| 2482 |
-
"mtp.layers.0.mlp.experts.92.up_proj",
|
| 2483 |
-
"mtp.layers.0.mlp.experts.93.down_proj",
|
| 2484 |
-
"mtp.layers.0.mlp.experts.93.gate_proj",
|
| 2485 |
-
"mtp.layers.0.mlp.experts.93.up_proj",
|
| 2486 |
-
"mtp.layers.0.mlp.experts.94.down_proj",
|
| 2487 |
-
"mtp.layers.0.mlp.experts.94.gate_proj",
|
| 2488 |
-
"mtp.layers.0.mlp.experts.94.up_proj",
|
| 2489 |
-
"mtp.layers.0.mlp.experts.95.down_proj",
|
| 2490 |
-
"mtp.layers.0.mlp.experts.95.gate_proj",
|
| 2491 |
-
"mtp.layers.0.mlp.experts.95.up_proj",
|
| 2492 |
-
"mtp.layers.0.mlp.experts.96.down_proj",
|
| 2493 |
-
"mtp.layers.0.mlp.experts.96.gate_proj",
|
| 2494 |
-
"mtp.layers.0.mlp.experts.96.up_proj",
|
| 2495 |
-
"mtp.layers.0.mlp.experts.97.down_proj",
|
| 2496 |
-
"mtp.layers.0.mlp.experts.97.gate_proj",
|
| 2497 |
-
"mtp.layers.0.mlp.experts.97.up_proj",
|
| 2498 |
-
"mtp.layers.0.mlp.experts.98.down_proj",
|
| 2499 |
-
"mtp.layers.0.mlp.experts.98.gate_proj",
|
| 2500 |
-
"mtp.layers.0.mlp.experts.98.up_proj",
|
| 2501 |
-
"mtp.layers.0.mlp.experts.99.down_proj",
|
| 2502 |
-
"mtp.layers.0.mlp.experts.99.gate_proj",
|
| 2503 |
-
"mtp.layers.0.mlp.experts.99.up_proj",
|
| 2504 |
"mtp.layers.0.mlp.gate",
|
| 2505 |
"mtp.layers.0.mlp.shared_expert.down_proj",
|
| 2506 |
"mtp.layers.0.mlp.shared_expert.gate_proj",
|
|
@@ -2520,7 +983,7 @@
|
|
| 2520 |
"kv_cache_quant_config": {},
|
| 2521 |
"kv_cache_post_rope": false,
|
| 2522 |
"quant_mode": "eager_mode",
|
| 2523 |
-
"version": "0.
|
| 2524 |
"export": {
|
| 2525 |
"kv_cache_group": [],
|
| 2526 |
"min_kv_scale": 0.0,
|
|
|
|
| 964 |
"model.visual.blocks.9.norm2",
|
| 965 |
"model.visual.merger.linear_fc1",
|
| 966 |
"model.visual.merger.linear_fc2",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 967 |
"mtp.layers.0.mlp.gate",
|
| 968 |
"mtp.layers.0.mlp.shared_expert.down_proj",
|
| 969 |
"mtp.layers.0.mlp.shared_expert.gate_proj",
|
|
|
|
| 983 |
"kv_cache_quant_config": {},
|
| 984 |
"kv_cache_post_rope": false,
|
| 985 |
"quant_mode": "eager_mode",
|
| 986 |
+
"version": "0.12+6b1a3c15e5e",
|
| 987 |
"export": {
|
| 988 |
"kv_cache_group": [],
|
| 989 |
"min_kv_scale": 0.0,
|
model.safetensors-00001-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8b83709a460f87dfaf304923909a38de285c670df2e200b119cd9d8c3622783
|
| 3 |
size 2281988744
|
model.safetensors-00002-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a0cfcb889cf594712dcf0ccce0700b8547b01f2bb50511c51a27ef701506b48
|
| 3 |
size 2281988744
|
model.safetensors-00003-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eee99d7ebe49f6940fe37750d617bdb9bb6429b237973337389e1173525d0765
|
| 3 |
size 2281988744
|
model.safetensors-00004-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:450e0b4eec152e6ab6c3b43df940be47b2895aae72794b7b17df529205a8cceb
|
| 3 |
size 2281986696
|
model.safetensors-00005-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:099820b92ab919c4cc942a672b8644b90a935544f4dc7a44fa781c13e8975181
|
| 3 |
size 2281986696
|
model.safetensors-00006-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:527d1e4f47826ad0a9c960067895966cedb29ac698713434530ec48feaecc4ee
|
| 3 |
size 2281988744
|
model.safetensors-00007-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83329bfdec2680e8c7f79736ac23389550757a6e15a7d8da534f70b398f08a3f
|
| 3 |
size 2281988744
|
model.safetensors-00008-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12b15372ff5841e5e26badb56ee5645f5acdc35b8b62dcde7db54927163fed6f
|
| 3 |
size 2281988744
|
model.safetensors-00009-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9fae295d14c9f529435ff345a802008fa58d8de3128b84d635869598c83f7bc
|
| 3 |
size 2281988744
|
model.safetensors-00010-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e36bb40963c16d655c19241a43d4d32bb96db1209fec35ada607ac2ff467775
|
| 3 |
size 2281988744
|
model.safetensors-00011-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72278c458869953b58eb5db592632fa4090491dc1deb3c9cc0e7d2dd10ce6d02
|
| 3 |
size 2281988744
|
model.safetensors-00012-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdde75d2d9089a04c8dcb5e2473599e7f886b686c7057f7a1d3054fef932f28d
|
| 3 |
size 2281988744
|
model.safetensors-00013-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9abd1d6d6e857f90dabf458a62f6e0cc88247c844db42e5c84145eb9e7350213
|
| 3 |
size 2281988744
|
model.safetensors-00014-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f18b635663e7c0fa69af09976eaec785cd586ea376229496798682d2d37a735e
|
| 3 |
size 2281988744
|
model.safetensors-00015-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a0f527d8360d6cf4a13d7b04b432fc2b3dd1a9eb6018a042d1c59ab312249c6
|
| 3 |
size 2281988744
|
model.safetensors-00016-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da89af735bb1cc45cff2c59ca5655966ac18f278601b280b3332d06fa0a1be40
|
| 3 |
size 2281986696
|
model.safetensors-00017-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7094ac1fe434fce359d2cf8ffe30a37669526c1f78a809886f62bf7f8c2e45d
|
| 3 |
size 2281988744
|
model.safetensors-00018-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2baa70d163c65047f4f63419529d17a8aed77413c9baad68445898134defc4a
|
| 3 |
size 2281986696
|
model.safetensors-00019-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd6e0c87cb21bfca1c39098ca43578d422ee14a5aa773f8dc24ab1b0bfc401cd
|
| 3 |
size 2281986696
|
model.safetensors-00020-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f664716af0f3c341c9527e347394a206ad37444d5ae17c0c4fd61f4218be22b9
|
| 3 |
size 2281988744
|
model.safetensors-00021-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fca84617a337b629ac41745f9d7d11a613cdf202db710455aa3d4a00ae81a221
|
| 3 |
size 2281988744
|
model.safetensors-00022-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f78ac70f346a5e39c6425a914477293763545f1c2e5e36e74133e9daac419cae
|
| 3 |
size 2281988744
|
model.safetensors-00023-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f26f5dfecff6fc07c25f55b2e15dcfc928e58905c6b1a139b610251aac15afaf
|
| 3 |
size 2281988744
|
model.safetensors-00024-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:440a8928cecc616afb8cd6fd62be75a357f083658a4141bf89a2396ca7e16f44
|
| 3 |
size 2281988744
|
model.safetensors-00025-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaa666b259aece55bf8d4e01ef9f8f9ef850fd5bf88bcacf32ee8df9ef260810
|
| 3 |
size 2281988744
|
model.safetensors-00026-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0c3061339b73b5133772742d054fcf7536ab30f1779fd71e73ebe6029e243c9
|
| 3 |
size 2281988744
|
model.safetensors-00027-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33f66d1c9a297e1d78b075eecee423b8f68a52fbc8248a33871ce9391069a841
|
| 3 |
size 2281988744
|
model.safetensors-00028-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e3404ac0c3b9f61562996da644bf2e97990cd2b773dc37bb4dcf507f260552
|
| 3 |
size 2281986696
|
model.safetensors-00029-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9eb5f1d5d6880e3d87b1bc130a56b4d71cc4877fa7f819e541b92c2e44f433bb
|
| 3 |
size 2281986696
|
model.safetensors-00030-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6c9eae839b05a1d7c76a50d8bed7841a26b5242110455c7271d60a3bcf2f672
|
| 3 |
size 2281988744
|
model.safetensors-00031-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dc8e6dc5c205dd786fc77cb38dd205cb26967fb79a3a5d83d1878c0cdd6ac97
|
| 3 |
size 2281986696
|
model.safetensors-00032-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb058813f5438d63324f6e36b392b5257987c8a26a0ff84ab48308652ff03733
|
| 3 |
size 2281988744
|
model.safetensors-00033-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4c96dff6a444fa827db23137d12cf6c278b03b4604994a86be9be0e2c34c225
|
| 3 |
size 2281988744
|
model.safetensors-00034-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6eb8f4cdf4ce7b9a22077966000b21a4dd12eb7075053afff79bbb6e7ef8810
|
| 3 |
size 2281988744
|
model.safetensors-00035-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5255cb94f24fbee07952a47146b54b9b23d2c765316df60780533e290d22be8a
|
| 3 |
size 2281986696
|
model.safetensors-00036-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4162243814c73ae247f9ef0c66ea94f8a0ae7f2b121875f44c22a6aa435ef14
|
| 3 |
size 2281988744
|
model.safetensors-00037-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baddc08ebd62e8dc6ea2068b43f2076d4a945cd4c94468a17465948e29a2c03e
|
| 3 |
size 2281988744
|
model.safetensors-00038-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed92df8b3692fe718a18d5764be951cff2e5fc434ba82774e2b979d8848c517b
|
| 3 |
size 2281988744
|
model.safetensors-00039-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8adf36b774dcf52bd681edaaa63eb7f5dbad9b08c0d85c4ecac584d3c2e59f55
|
| 3 |
size 2281988744
|
model.safetensors-00040-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:101cf1ddd548260d1f262b976966c313f5357168cb134506b829549a058f4c6f
|
| 3 |
size 2281988744
|
model.safetensors-00041-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38263863acc0f5cb1a0dbb1a196dec9b32a7e9aad1587d637363bab6f02f6b4a
|
| 3 |
size 2281988744
|
model.safetensors-00042-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f39cc2ffada952fd8c1747e11fe6fef7b9f0eeb121bfddcb8cbb8920952ea661
|
| 3 |
size 2281988744
|
model.safetensors-00043-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ee4af94802ba5c09da8267fbb3477c366e3cfe36bf17d93cc064c346bedefb9
|
| 3 |
size 2281988744
|
model.safetensors-00044-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f349e3404a58e255c5fed214f3da64e66a2f06adb9eb184ffd27fe82be61848
|
| 3 |
size 2281988744
|
model.safetensors-00045-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281986696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f02f96eb5e350c40566bd185de3f41ada8a3965a5ce27f8ef65d5230c447ef17
|
| 3 |
size 2281986696
|
model.safetensors-00046-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4e63a0e095b1e04f36df0c33a6a5a20062d604a8dc0b2e242c1a96f3b487310
|
| 3 |
size 2281988744
|
model.safetensors-00047-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1fb49043d8f74a0ae9e6d9570049fdc5dab5863ba8d4ce425c58ffd6dd07b24
|
| 3 |
size 2281988744
|
model.safetensors-00048-of-00094.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2281988744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b23e28a48fb60256c015c9d4745b0229c256ab7365e22dd532fa2c8f85c37d3d
|
| 3 |
size 2281988744
|