Hugging Face's logo

yuvraj17
/
Llama-3-8B-spectrum-25

Text Generation
Transformers
PyTorch
Safetensors
llama
axolotl
Generated from Trainer
spectrum finetuning
Deepspeed MultiGPU
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
yuvraj17 commited on
Commit
158dfb9
•
1 Parent(s): a237ae0

End of training

Browse files
Files changed (7) hide show
  1. README.md +293 -0
  2. generation_config.json +12 -0
  3. pytorch_model-00001-of-00004.bin +3 -0
  4. pytorch_model-00002-of-00004.bin +3 -0
  5. pytorch_model-00003-of-00004.bin +3 -0
  6. pytorch_model-00004-of-00004.bin +3 -0
  7. pytorch_model.bin.index.json +298 -0
README.md ADDED
@@ -0,0 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Llama-3-8B-spectrum-25
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.4.1`
20
+ ```yaml
21
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
22
+ model_type: LlamaForCausalLM
23
+ tokenizer_type: AutoTokenizer
24
+ is_llama_derived_model: true
25
+ tokenizer_use_fast: true
26
+ hub_model_id: Llama-3-8B-spectrum-25
27
+
28
+ # load_in_8bit: true
29
+ # load_in_4bit: false
30
+ # strict: false
31
+
32
+ datasets:
33
+ - path: yuvraj17/finetune_alpaca_1K
34
+ type: alpaca
35
+
36
+ dataset_prepared_path: last_run_prepared
37
+ val_set_size: 0.02
38
+ output_dir: ./outputs/llama-3-8b-spectrum-25
39
+
40
+ sequence_len: 2048
41
+ sample_packing: false
42
+ eval_sample_packing: false
43
+ pad_to_sequence_len: true
44
+
45
+ # Model Layers for Llama-3-8B-Instruct (Spectrum with snr values (25%)):
46
+ unfrozen_parameters:
47
+ - ^lm_head.weight$
48
+ - ^model.embed_tokens.weight$
49
+ # input_layernorm layers
50
+ - model.layers.0.input_layernorm
51
+ - model.layers.1.input_layernorm
52
+ - model.layers.2.input_layernorm
53
+ - model.layers.3.input_layernorm
54
+ - model.layers.4.input_layernorm
55
+ - model.layers.5.input_layernorm
56
+ - model.layers.6.input_layernorm
57
+ - model.layers.7.input_layernorm
58
+ # lm_head layers
59
+ # mlp.down_proj layers
60
+ - model.layers.1.mlp.down_proj
61
+ - model.layers.0.mlp.down_proj
62
+ - model.layers.2.mlp.down_proj
63
+ - model.layers.30.mlp.down_proj
64
+ - model.layers.22.mlp.down_proj
65
+ - model.layers.21.mlp.down_proj
66
+ - model.layers.5.mlp.down_proj
67
+ - model.layers.29.mlp.down_proj
68
+ # mlp.gate_proj layers
69
+ - model.layers.1.mlp.gate_proj
70
+ - model.layers.2.mlp.gate_proj
71
+ - model.layers.3.mlp.gate_proj
72
+ - model.layers.0.mlp.gate_proj
73
+ - model.layers.4.mlp.gate_proj
74
+ - model.layers.25.mlp.gate_proj
75
+ - model.layers.26.mlp.gate_proj
76
+ - model.layers.5.mlp.gate_proj
77
+ # mlp.up_proj layers
78
+ - model.layers.4.mlp.up_proj
79
+ - model.layers.0.mlp.up_proj
80
+ - model.layers.3.mlp.up_proj
81
+ - model.layers.5.mlp.up_proj
82
+ - model.layers.7.mlp.up_proj
83
+ - model.layers.6.mlp.up_proj
84
+ - model.layers.2.mlp.up_proj
85
+ - model.layers.1.mlp.up_proj
86
+ # model.embed_tokens layers
87
+ # model.norm layers
88
+ # post_attention_layernorm layers
89
+ - model.layers.0.post_attention_layernorm
90
+ - model.layers.1.post_attention_layernorm
91
+ - model.layers.2.post_attention_layernorm
92
+ - model.layers.3.post_attention_layernorm
93
+ - model.layers.4.post_attention_layernorm
94
+ - model.layers.5.post_attention_layernorm
95
+ - model.layers.6.post_attention_layernorm
96
+ - model.layers.7.post_attention_layernorm
97
+ # self_attn.k_proj layers
98
+ - model.layers.29.self_attn.k_proj
99
+ - model.layers.25.self_attn.k_proj
100
+ - model.layers.23.self_attn.k_proj
101
+ - model.layers.28.self_attn.k_proj
102
+ - model.layers.21.self_attn.k_proj
103
+ - model.layers.19.self_attn.k_proj
104
+ - model.layers.22.self_attn.k_proj
105
+ - model.layers.20.self_attn.k_proj
106
+ # self_attn.o_proj layers
107
+ - model.layers.14.self_attn.o_proj
108
+ - model.layers.7.self_attn.o_proj
109
+ - model.layers.5.self_attn.o_proj
110
+ - model.layers.11.self_attn.o_proj
111
+ - model.layers.9.self_attn.o_proj
112
+ - model.layers.6.self_attn.o_proj
113
+ - model.layers.13.self_attn.o_proj
114
+ - model.layers.10.self_attn.o_proj
115
+ # self_attn.q_proj layers
116
+ - model.layers.13.self_attn.q_proj
117
+ - model.layers.9.self_attn.q_proj
118
+ - model.layers.10.self_attn.q_proj
119
+ - model.layers.8.self_attn.q_proj
120
+ - model.layers.14.self_attn.q_proj
121
+ - model.layers.11.self_attn.q_proj
122
+ - model.layers.0.self_attn.q_proj
123
+ - model.layers.15.self_attn.q_proj
124
+ # self_attn.v_proj layers
125
+ - model.layers.26.self_attn.v_proj
126
+ - model.layers.17.self_attn.v_proj
127
+ - model.layers.28.self_attn.v_proj
128
+ - model.layers.3.self_attn.v_proj
129
+ - model.layers.29.self_attn.v_proj
130
+ - model.layers.21.self_attn.v_proj
131
+ - model.layers.16.self_attn.v_proj
132
+ - model.layers.15.self_attn.v_proj
133
+
134
+ # adapter: lora
135
+ # lora_model_dir:
136
+ # lora_r: 32
137
+ # lora_alpha: 16
138
+ # lora_dropout: 0.05
139
+ # lora_target_linear: true
140
+ # lora_fan_in_fan_out:
141
+
142
+ wandb_project: llama-3-8B-spectrum
143
+ wandb_entity:
144
+ wandb_watch:
145
+ wandb_name:
146
+ wandb_log_model:
147
+
148
+ gradient_accumulation_steps: 4
149
+ micro_batch_size: 4
150
+ num_epochs: 2
151
+ optimizer: paged_adamw_32bit
152
+ lr_scheduler: cosine
153
+ learning_rate: 0.0002
154
+
155
+ train_on_inputs: false
156
+ group_by_length: false
157
+ bf16: auto
158
+ fp16:
159
+ tf32: false
160
+
161
+ gradient_checkpointing: true
162
+ early_stopping_patience:
163
+ resume_from_checkpoint:
164
+ local_rank:
165
+ logging_steps: 1
166
+ xformers_attention:
167
+ flash_attention: true
168
+
169
+ warmup_steps: 100
170
+ eval_steps: 0.01
171
+ save_strategy: epoch
172
+ save_steps:
173
+ debug:
174
+ deepspeed: deepspeed_configs/zero2.json
175
+ weight_decay: 0.1
176
+ fsdp:
177
+ fsdp_config:
178
+ special_tokens:
179
+ pad_token: "<|end_of_text|>"
180
+
181
+ ```
182
+
183
+ </details><br>
184
+
185
+ # Llama-3-8B-spectrum-25
186
+
187
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
188
+ It achieves the following results on the evaluation set:
189
+ - Loss: 1.2791
190
+
191
+ ## Model description
192
+
193
+ More information needed
194
+
195
+ ## Intended uses & limitations
196
+
197
+ More information needed
198
+
199
+ ## Training and evaluation data
200
+
201
+ More information needed
202
+
203
+ ## Training procedure
204
+
205
+ ### Training hyperparameters
206
+
207
+ The following hyperparameters were used during training:
208
+ - learning_rate: 0.0002
209
+ - train_batch_size: 4
210
+ - eval_batch_size: 4
211
+ - seed: 42
212
+ - distributed_type: multi-GPU
213
+ - num_devices: 2
214
+ - gradient_accumulation_steps: 4
215
+ - total_train_batch_size: 32
216
+ - total_eval_batch_size: 8
217
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
218
+ - lr_scheduler_type: cosine
219
+ - lr_scheduler_warmup_steps: 100
220
+ - num_epochs: 2
221
+
222
+ ### Training results
223
+
224
+ | Training Loss | Epoch | Step | Validation Loss |
225
+ |:-------------:|:------:|:----:|:---------------:|
226
+ | 1.4618 | 0.0325 | 1 | 1.2057 |
227
+ | 1.2189 | 0.0650 | 2 | 1.1976 |
228
+ | 1.0899 | 0.0976 | 3 | 1.1611 |
229
+ | 1.2787 | 0.1301 | 4 | 1.1385 |
230
+ | 1.1341 | 0.1626 | 5 | 1.1368 |
231
+ | 1.2793 | 0.1951 | 6 | 1.1228 |
232
+ | 1.2094 | 0.2276 | 7 | 1.1123 |
233
+ | 1.3289 | 0.2602 | 8 | 1.1126 |
234
+ | 1.1179 | 0.2927 | 9 | 1.1123 |
235
+ | 1.2456 | 0.3252 | 10 | 1.1109 |
236
+ | 1.2253 | 0.3577 | 11 | 1.1083 |
237
+ | 1.2563 | 0.3902 | 12 | 1.1079 |
238
+ | 1.3222 | 0.4228 | 13 | 1.1059 |
239
+ | 1.2197 | 0.4553 | 14 | 1.1080 |
240
+ | 1.1862 | 0.4878 | 15 | 1.1054 |
241
+ | 1.1136 | 0.5203 | 16 | 1.1040 |
242
+ | 1.2221 | 0.5528 | 17 | 1.1040 |
243
+ | 1.4475 | 0.5854 | 18 | 1.1049 |
244
+ | 1.0187 | 0.6179 | 19 | 1.1054 |
245
+ | 1.0596 | 0.6504 | 20 | 1.1057 |
246
+ | 1.2075 | 0.6829 | 21 | 1.1063 |
247
+ | 1.0671 | 0.7154 | 22 | 1.1062 |
248
+ | 1.2115 | 0.7480 | 23 | 1.1059 |
249
+ | 1.1137 | 0.7805 | 24 | 1.1061 |
250
+ | 1.5483 | 0.8130 | 25 | 1.1097 |
251
+ | 1.369 | 0.8455 | 26 | 1.1120 |
252
+ | 1.0528 | 0.8780 | 27 | 1.1155 |
253
+ | 1.2126 | 0.9106 | 28 | 1.1169 |
254
+ | 1.0164 | 0.9431 | 29 | 1.1167 |
255
+ | 1.2082 | 0.9756 | 30 | 1.1183 |
256
+ | 1.0256 | 1.0081 | 31 | 1.1191 |
257
+ | 0.6859 | 1.0407 | 32 | 1.1267 |
258
+ | 0.722 | 1.0732 | 33 | 1.1505 |
259
+ | 0.7161 | 1.1057 | 34 | 1.1719 |
260
+ | 0.724 | 1.1382 | 35 | 1.1829 |
261
+ | 0.67 | 1.1707 | 36 | 1.1844 |
262
+ | 0.5737 | 1.2033 | 37 | 1.1874 |
263
+ | 0.7081 | 1.2358 | 38 | 1.1940 |
264
+ | 0.7239 | 1.2683 | 39 | 1.1978 |
265
+ | 0.5927 | 1.3008 | 40 | 1.2022 |
266
+ | 0.6079 | 1.3333 | 41 | 1.2070 |
267
+ | 0.6427 | 1.3659 | 42 | 1.2104 |
268
+ | 0.506 | 1.3984 | 43 | 1.2134 |
269
+ | 0.4582 | 1.4309 | 44 | 1.2195 |
270
+ | 0.7492 | 1.4634 | 45 | 1.2208 |
271
+ | 0.538 | 1.4959 | 46 | 1.2258 |
272
+ | 0.7147 | 1.5285 | 47 | 1.2299 |
273
+ | 0.6565 | 1.5610 | 48 | 1.2339 |
274
+ | 0.8011 | 1.5935 | 49 | 1.2365 |
275
+ | 0.6986 | 1.6260 | 50 | 1.2396 |
276
+ | 0.7924 | 1.6585 | 51 | 1.2472 |
277
+ | 0.8128 | 1.6911 | 52 | 1.2542 |
278
+ | 0.6733 | 1.7236 | 53 | 1.2616 |
279
+ | 0.7363 | 1.7561 | 54 | 1.2693 |
280
+ | 0.5815 | 1.7886 | 55 | 1.2762 |
281
+ | 0.6571 | 1.8211 | 56 | 1.2750 |
282
+ | 0.6985 | 1.8537 | 57 | 1.2748 |
283
+ | 0.7519 | 1.8862 | 58 | 1.2715 |
284
+ | 0.8171 | 1.9187 | 59 | 1.2733 |
285
+ | 0.7373 | 1.9512 | 60 | 1.2791 |
286
+
287
+
288
+ ### Framework versions
289
+
290
+ - Transformers 4.44.2
291
+ - Pytorch 2.4.0+cu121
292
+ - Datasets 2.20.0
293
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 4096,
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcc7c3471a63040c3116326aaafde46b50ba3001e34eed13824fb1ea63176a4
3
+ size 5591015801
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc34a2445b92244877ad11e5af59537dc601436fa44bbb47606bf2e5243f690
3
+ size 4932819445
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9dc110b89cf011b370a94e4cc19b4ffca0bf5164aaf6d25db7ce254d9367022
3
+ size 4983081850
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72bb339b02845928a7491ab5a742b254415dd31f85047f0bce7fb6abd28ca039
3
+ size 553694356
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
296
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin"
297
+ }
298
+ }