taozi555 commited on
Commit
ca097d3
·
verified ·
1 Parent(s): e6712d4

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ datasets:
9
+ - lightblue/gpt4_conversations_multilingual
10
+ - Nopm/Opus_WritingStruct
11
+ model-index:
12
+ - name: hiwaifu-12b
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ [<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)
20
+ <details><summary>See axolotl config</summary>
21
+
22
+ axolotl version: `0.8.1`
23
+ ```yaml
24
+ base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
25
+ model_type: AutoModelForCausalLM
26
+ tokenizer_type: AutoTokenizer
27
+
28
+ hub_model_id: taozi555/hiwaifu-12b
29
+ hub_strategy: "all_checkpoints"
30
+ push_dataset_to_hub:
31
+ hf_use_auth_token: true
32
+
33
+ plugins:
34
+ - axolotl.integrations.liger.LigerPlugin
35
+ liger_rope: true
36
+ liger_rms_norm: true
37
+ liger_swiglu: true
38
+ liger_fused_linear_cross_entropy: true
39
+
40
+ load_in_8bit: false
41
+ load_in_4bit: false
42
+ strict: false
43
+
44
+ datasets:
45
+ - path: /root/taozi555/deepseek-rp/model12_digg1_safe.jsonl
46
+ conversation: chatml
47
+ type: chat_template
48
+ field_messages: conversations
49
+ message_field_role: role
50
+ message_field_content: content
51
+ - path: /root/taozi555/deepseek-rp/model12_digg1_unsafe.jsonl
52
+ conversation: chatml
53
+ type: chat_template
54
+ field_messages: conversations
55
+ message_field_role: role
56
+ message_field_content: content
57
+ - path: /root/taozi555/deepseek-rp/model2_digg1_unsafe.jsonl
58
+ conversation: chatml
59
+ type: chat_template
60
+ field_messages: conversations
61
+ message_field_role: role
62
+ message_field_content: content
63
+ - path: /root/taozi555/deepseek-rp/model2_digg1_safe.jsonl
64
+ conversation: chatml
65
+ type: chat_template
66
+ field_messages: conversations
67
+ message_field_role: role
68
+ message_field_content: content
69
+ - path: /root/processed_SCP_40k_dataset
70
+ conversation: chatml
71
+ type: chat_template
72
+ field_messages: conversations
73
+ message_field_role: from
74
+ message_field_content: value
75
+ split: train
76
+ - path: lightblue/gpt4_conversations_multilingual
77
+ conversation: chatml
78
+ type: chat_template
79
+ field_messages: conversations
80
+ message_field_role: from
81
+ message_field_content: value
82
+ split: train
83
+ - path: Nopm/Opus_WritingStruct
84
+ conversation: chatml
85
+ type: chat_template
86
+ #field_messages: messages
87
+ message_field_role: role
88
+ message_field_content: content
89
+ split: train
90
+ # - path: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
91
+ # conversation: chatml
92
+ # type: chat_template
93
+ # field_messages: conversations
94
+ # message_field_role: from
95
+ # message_field_content: value
96
+ # split: train
97
+ chat_template: chatml
98
+ shuffle_merged_datasets: true
99
+ default_system_message: "You are the JadeSpeech model from the HiWaifu App."
100
+ dataset_prepared_path: /root/autodl-tmp/data/
101
+ val_set_size: 0.05
102
+ output_dir: /root/autodl-tmp/hiwaifu-12b/
103
+
104
+ sequence_len: 32768
105
+ sample_packing: true
106
+ pad_to_sequence_len: true
107
+
108
+ adapter:
109
+ lora_model_dir:
110
+ lora_r:
111
+ lora_alpha:
112
+ lora_dropout:
113
+ lora_target_linear:
114
+ lora_fan_in_fan_out:
115
+
116
+ wandb_project: hiwaifu-12b-v4
117
+ wandb_entity:
118
+ wandb_watch:
119
+ wandb_name: hiwaifu-12b-v4
120
+ wandb_log_model:
121
+
122
+ gradient_accumulation_steps: 2
123
+ micro_batch_size: 1
124
+ num_epochs: 2
125
+ optimizer: adamw_bnb_8bit
126
+ lr_scheduler: cosine
127
+ learning_rate: 0.00005
128
+
129
+ train_on_inputs: false
130
+ group_by_length: false
131
+ bf16: auto
132
+ fp16:
133
+ tf32: false
134
+
135
+ gradient_checkpointing: true
136
+ early_stopping_patience:
137
+ resume_from_checkpoint: /root/autodl-tmp/hiwaifu-12b/checkpoint-1030
138
+ local_rank:
139
+ logging_steps: 1
140
+ xformers_attention:
141
+ flash_attention: true
142
+
143
+ warmup_steps: 40
144
+ evals_per_epoch:
145
+ eval_table_size:
146
+ eval_max_new_tokens:
147
+ saves_per_epoch: 2
148
+ debug:
149
+ deepspeed: /root/deepspeed_configs/zero3_bf16.json
150
+ weight_decay: 0.1
151
+ fsdp:
152
+ fsdp_config:
153
+ special_tokens:
154
+ pad_token: <pad>
155
+ ```
156
+
157
+ </details><br>
158
+
159
+ # hiwaifu-12b
160
+
161
+ This model is a fine-tuned version of [IntervitensInc/Mistral-Nemo-Base-2407-chatml](https://huggingface.co/IntervitensInc/Mistral-Nemo-Base-2407-chatml) on the /root/taozi555/deepseek-rp/model12_digg1_safe.jsonl, the /root/taozi555/deepseek-rp/model12_digg1_unsafe.jsonl, the /root/taozi555/deepseek-rp/model2_digg1_unsafe.jsonl, the /root/taozi555/deepseek-rp/model2_digg1_safe.jsonl, the lightblue/gpt4_conversations_multilingual and the Nopm/Opus_WritingStruct datasets.
162
+ It achieves the following results on the evaluation set:
163
+ - Loss: 0.1903
164
+
165
+ ## Model description
166
+
167
+ More information needed
168
+
169
+ ## Intended uses & limitations
170
+
171
+ More information needed
172
+
173
+ ## Training and evaluation data
174
+
175
+ More information needed
176
+
177
+ ## Training procedure
178
+
179
+ ### Training hyperparameters
180
+
181
+ The following hyperparameters were used during training:
182
+ - learning_rate: 5e-05
183
+ - train_batch_size: 1
184
+ - eval_batch_size: 1
185
+ - seed: 42
186
+ - distributed_type: multi-GPU
187
+ - num_devices: 5
188
+ - gradient_accumulation_steps: 2
189
+ - total_train_batch_size: 10
190
+ - total_eval_batch_size: 5
191
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
192
+ - lr_scheduler_type: cosine
193
+ - lr_scheduler_warmup_steps: 40
194
+ - num_epochs: 2.0
195
+
196
+ ### Training results
197
+
198
+ | Training Loss | Epoch | Step | Validation Loss |
199
+ |:-------------:|:-----:|:----:|:---------------:|
200
+ | 0.1899 | 2.0 | 1466 | 0.1903 |
201
+
202
+
203
+ ### Framework versions
204
+
205
+ - Transformers 4.51.0
206
+ - Pytorch 2.5.1+cu124
207
+ - Datasets 3.5.0
208
+ - Tokenizers 0.21.1
README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ datasets:
9
+ - lightblue/gpt4_conversations_multilingual
10
+ - Nopm/Opus_WritingStruct
11
+ model-index:
12
+ - name: hiwaifu-12b
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ [<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)
20
+ <details><summary>See axolotl config</summary>
21
+
22
+ axolotl version: `0.8.1`
23
+ ```yaml
24
+ base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
25
+ model_type: AutoModelForCausalLM
26
+ tokenizer_type: AutoTokenizer
27
+
28
+ hub_model_id: taozi555/hiwaifu-12b
29
+ hub_strategy: "all_checkpoints"
30
+ push_dataset_to_hub:
31
+ hf_use_auth_token: true
32
+
33
+ plugins:
34
+ - axolotl.integrations.liger.LigerPlugin
35
+ liger_rope: true
36
+ liger_rms_norm: true
37
+ liger_swiglu: true
38
+ liger_fused_linear_cross_entropy: true
39
+
40
+ load_in_8bit: false
41
+ load_in_4bit: false
42
+ strict: false
43
+
44
+ datasets:
45
+ - path: /root/taozi555/deepseek-rp/model12_digg1_safe.jsonl
46
+ conversation: chatml
47
+ type: chat_template
48
+ field_messages: conversations
49
+ message_field_role: role
50
+ message_field_content: content
51
+ - path: /root/taozi555/deepseek-rp/model12_digg1_unsafe.jsonl
52
+ conversation: chatml
53
+ type: chat_template
54
+ field_messages: conversations
55
+ message_field_role: role
56
+ message_field_content: content
57
+ - path: /root/taozi555/deepseek-rp/model2_digg1_unsafe.jsonl
58
+ conversation: chatml
59
+ type: chat_template
60
+ field_messages: conversations
61
+ message_field_role: role
62
+ message_field_content: content
63
+ - path: /root/taozi555/deepseek-rp/model2_digg1_safe.jsonl
64
+ conversation: chatml
65
+ type: chat_template
66
+ field_messages: conversations
67
+ message_field_role: role
68
+ message_field_content: content
69
+ - path: /root/processed_SCP_40k_dataset
70
+ conversation: chatml
71
+ type: chat_template
72
+ field_messages: conversations
73
+ message_field_role: from
74
+ message_field_content: value
75
+ split: train
76
+ - path: lightblue/gpt4_conversations_multilingual
77
+ conversation: chatml
78
+ type: chat_template
79
+ field_messages: conversations
80
+ message_field_role: from
81
+ message_field_content: value
82
+ split: train
83
+ - path: Nopm/Opus_WritingStruct
84
+ conversation: chatml
85
+ type: chat_template
86
+ #field_messages: messages
87
+ message_field_role: role
88
+ message_field_content: content
89
+ split: train
90
+ # - path: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
91
+ # conversation: chatml
92
+ # type: chat_template
93
+ # field_messages: conversations
94
+ # message_field_role: from
95
+ # message_field_content: value
96
+ # split: train
97
+ chat_template: chatml
98
+ shuffle_merged_datasets: true
99
+ default_system_message: "You are the JadeSpeech model from the HiWaifu App."
100
+ dataset_prepared_path: /root/autodl-tmp/data/
101
+ val_set_size: 0.05
102
+ output_dir: /root/autodl-tmp/hiwaifu-12b/
103
+
104
+ sequence_len: 32768
105
+ sample_packing: true
106
+ pad_to_sequence_len: true
107
+
108
+ adapter:
109
+ lora_model_dir:
110
+ lora_r:
111
+ lora_alpha:
112
+ lora_dropout:
113
+ lora_target_linear:
114
+ lora_fan_in_fan_out:
115
+
116
+ wandb_project: hiwaifu-12b-v4
117
+ wandb_entity:
118
+ wandb_watch:
119
+ wandb_name: hiwaifu-12b-v4
120
+ wandb_log_model:
121
+
122
+ gradient_accumulation_steps: 2
123
+ micro_batch_size: 1
124
+ num_epochs: 2
125
+ optimizer: adamw_bnb_8bit
126
+ lr_scheduler: cosine
127
+ learning_rate: 0.00005
128
+
129
+ train_on_inputs: false
130
+ group_by_length: false
131
+ bf16: auto
132
+ fp16:
133
+ tf32: false
134
+
135
+ gradient_checkpointing: true
136
+ early_stopping_patience:
137
+ resume_from_checkpoint: /root/autodl-tmp/hiwaifu-12b/checkpoint-1030
138
+ local_rank:
139
+ logging_steps: 1
140
+ xformers_attention:
141
+ flash_attention: true
142
+
143
+ warmup_steps: 40
144
+ evals_per_epoch:
145
+ eval_table_size:
146
+ eval_max_new_tokens:
147
+ saves_per_epoch: 2
148
+ debug:
149
+ deepspeed: /root/deepspeed_configs/zero3_bf16.json
150
+ weight_decay: 0.1
151
+ fsdp:
152
+ fsdp_config:
153
+ special_tokens:
154
+ pad_token: <pad>
155
+ ```
156
+
157
+ </details><br>
158
+
159
+ # hiwaifu-12b
160
+
161
+ This model is a fine-tuned version of [IntervitensInc/Mistral-Nemo-Base-2407-chatml](https://huggingface.co/IntervitensInc/Mistral-Nemo-Base-2407-chatml) on the /root/taozi555/deepseek-rp/model12_digg1_safe.jsonl, the /root/taozi555/deepseek-rp/model12_digg1_unsafe.jsonl, the /root/taozi555/deepseek-rp/model2_digg1_unsafe.jsonl, the /root/taozi555/deepseek-rp/model2_digg1_safe.jsonl, the lightblue/gpt4_conversations_multilingual and the Nopm/Opus_WritingStruct datasets.
162
+ It achieves the following results on the evaluation set:
163
+ - Loss: 0.1903
164
+
165
+ ## Model description
166
+
167
+ More information needed
168
+
169
+ ## Intended uses & limitations
170
+
171
+ More information needed
172
+
173
+ ## Training and evaluation data
174
+
175
+ More information needed
176
+
177
+ ## Training procedure
178
+
179
+ ### Training hyperparameters
180
+
181
+ The following hyperparameters were used during training:
182
+ - learning_rate: 5e-05
183
+ - train_batch_size: 1
184
+ - eval_batch_size: 1
185
+ - seed: 42
186
+ - distributed_type: multi-GPU
187
+ - num_devices: 5
188
+ - gradient_accumulation_steps: 2
189
+ - total_train_batch_size: 10
190
+ - total_eval_batch_size: 5
191
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
192
+ - lr_scheduler_type: cosine
193
+ - lr_scheduler_warmup_steps: 40
194
+ - num_epochs: 2.0
195
+
196
+ ### Training results
197
+
198
+ | Training Loss | Epoch | Step | Validation Loss |
199
+ |:-------------:|:-----:|:----:|:---------------:|
200
+ | 0.1899 | 2.0 | 1466 | 0.1903 |
201
+
202
+
203
+ ### Framework versions
204
+
205
+ - Transformers 4.51.0
206
+ - Pytorch 2.5.1+cu124
207
+ - Datasets 3.5.0
208
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 15,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 1024000,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.51.0",
24
+ "use_cache": false,
25
+ "vocab_size": 131072
26
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.51.0"
7
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ffe0f20f7af9651def3a931474d3be35a13583fd60f107ff68232e74b6fde70
3
+ size 4865522496
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72df8bd42b1d94133fe5644b5026966058768149f6f305b56e1075453adca6b
3
+ size 4907529424
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4edc0f3cc6ef95ed4f0ce6b81e2ee6de553901c5ae609f1cc43b1c6885a81f9
3
+ size 4907529456
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77ed8dbde3bbdc0b46fe872d5347817f44fb727a3d2d336b90474b30efcdf36
3
+ size 4907529456
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a5f3d4c28f732abd2b333d1c6b653732a07bf951fb487229fbb5fe87344f1a
3
+ size 4907496272
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24495564800
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
368
+ "model.norm.weight": "model-00005-of-00005.safetensors"
369
+ }
370
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4c8fcd33487a449c07f423d47adb035bba8347ccf13eb074b4d1fef8acf919
3
+ size 17078288
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e5be6082fff2220945654961afb88126edc77b6958485090aaa247a1064f26
3
+ size 8888