Hugging Face's logo

decapoda-research
/
Adrastea-7b-v1.0-dpo

Text Generation
PEFT
Safetensors
mistral
Generated from Trainer
Model card Files Community
dustydecapod commited on
Commit
cf8ccda
·
1 Parent(s): 8905b87

initial commit

Browse files
Files changed (15) hide show
  1. README.md +225 -0
  2. added_tokens.json +4 -0
  3. axolotl.config +110 -0
  4. config.json +26 -0
  5. generation_config.json +6 -0
  6. model-00001-of-00006.safetensors +3 -0
  7. model-00002-of-00006.safetensors +3 -0
  8. model-00003-of-00006.safetensors +3 -0
  9. model-00004-of-00006.safetensors +3 -0
  10. model-00005-of-00006.safetensors +3 -0
  11. model-00006-of-00006.safetensors +3 -0
  12. model.safetensors.index.json +298 -0
  13. special_tokens_map.json +29 -0
  14. tokenizer.model +3 -0
  15. tokenizer_config.json +64 -0
README.md CHANGED
@@ -1,3 +1,228 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: rishiraj/CatPPT-base
7
  ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
13
+ <details><summary>See axolotl config</summary>
14
+
15
+ axolotl version: `0.3.0`
16
+ ```yaml
17
+ base_model: rishiraj/CatPPT-base
18
+ model_type: MistralForCausalLM
19
+ tokenizer_type: LlamaTokenizer
20
+ is_mistral_derived_model: true
21
+
22
+ load_in_8bit: false
23
+ load_in_4bit: true
24
+ strict: false
25
+
26
+ model_config:
27
+ output_router_logits: true
28
+
29
+ datasets:
30
+ - path: teknium/openhermes
31
+ type: alpaca
32
+ prompt_style: chatml
33
+ - path: garage-bAInd/Open-Platypus
34
+ type: alpaca
35
+ prompt_style: chatml
36
+ - path: LDJnr/Capybara
37
+ type: sharegpt
38
+ conversation: chatml
39
+ - path: datasets/samantha-1.1.json
40
+ type: sharegpt
41
+ conversation: chatml
42
+ - path: datasets/grammarly-coedit-alpaca.jsonl
43
+ type: alpaca
44
+ prompt_style: chatml
45
+ - path: datasets/dolphin-coder-codegen.jsonl
46
+ type: alpaca_w_system.load_open_orca_chatml
47
+ - path: datasets/dolphin-coder-translate.jsonl
48
+ type: alpaca_w_system.load_open_orca_chatml
49
+ - path: datasets/data-evol_instruct-decontaminated-alpaca.jsonl
50
+ type: alpaca
51
+ prompt_style: chatml
52
+ - path: datasets/data-oss_instruct-decontaminated-alpaca.jsonl
53
+ type: alpaca
54
+ prompt_style: chatml
55
+ - path: jondurbin/airoboros-3.2
56
+ type: sharegpt
57
+ conversations: chatml
58
+ dataset_prepared_path: last_run_prepared
59
+ val_set_size: 0.01
60
+ output_dir: ./qlora-out-2
61
+ seed: 420
62
+
63
+ adapter: qlora
64
+ lora_model_dir:
65
+
66
+ sequence_len: 8192
67
+ sample_packing: true
68
+ pad_to_sequence_len: true
69
+
70
+ lora_r: 32
71
+ lora_alpha: 16
72
+ lora_dropout: 0.05
73
+ lora_target_modules:
74
+ lora_target_linear: true
75
+ lora_fan_in_fan_out:
76
+ lora_modules_to_save:
77
+ - embed_tokens
78
+ - lm_head
79
+
80
+ wandb_project:
81
+ wandb_entity:
82
+ wandb_watch:
83
+ wandb_name:
84
+ wandb_log_model:
85
+
86
+ gradient_accumulation_steps: 2
87
+ micro_batch_size: 3
88
+ num_epochs: 1.5
89
+ optimizer: paged_adamw_8bit
90
+ lr_scheduler: cosine
91
+ learning_rate: 0.0002
92
+
93
+ train_on_inputs: false
94
+ group_by_length: false
95
+ bf16: true
96
+ fp16: false
97
+ tf32: false
98
+
99
+ gradient_checkpointing: true
100
+ early_stopping_patience:
101
+ resume_from_checkpoint:
102
+ local_rank:
103
+ logging_steps: 1
104
+ xformers_attention:
105
+ flash_attention: true
106
+
107
+ loss_watchdog_threshold: 5.0
108
+ loss_watchdog_patience: 3
109
+
110
+ warmup_steps: 0
111
+ evals_per_epoch: 20
112
+ eval_table_size:
113
+ saves_per_epoch: 20
114
+ debug:
115
+ deepspeed:
116
+ weight_decay: 0.05
117
+ fsdp:
118
+ fsdp_config:
119
+ special_tokens:
120
+ bos_token: "<s>"
121
+ eos_token: "</s>"
122
+ unk_token: "<unk>"
123
+ eos_token: "<|im_end|>"
124
+ tokens:
125
+ - "<|im_start|>"
126
+ trust_remote_code: true
127
+
128
+ ```
129
+
130
+ </details><br>
131
+
132
+ # qlora-out-2
133
+
134
+ This model is a fine-tuned version of [rishiraj/CatPPT-base](https://huggingface.co/rishiraj/CatPPT-base) on multiple datasets.
135
+ It achieves the following results on the evaluation set:
136
+ - Loss: 0.4258
137
+
138
+ ## Model description
139
+
140
+ More information needed
141
+
142
+ ## Intended uses & limitations
143
+
144
+ More information needed
145
+
146
+ ## Training and evaluation data
147
+
148
+ More information needed
149
+
150
+ ## Training procedure
151
+
152
+ ### Training hyperparameters
153
+
154
+ The following hyperparameters were used during training:
155
+ - learning_rate: 0.0002
156
+ - train_batch_size: 3
157
+ - eval_batch_size: 3
158
+ - seed: 420
159
+ - distributed_type: multi-GPU
160
+ - num_devices: 3
161
+ - gradient_accumulation_steps: 2
162
+ - total_train_batch_size: 18
163
+ - total_eval_batch_size: 9
164
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
165
+ - lr_scheduler_type: cosine
166
+ - num_epochs: 1.5
167
+
168
+ ### Training results
169
+
170
+ | Training Loss | Epoch | Step | Validation Loss |
171
+ |:-------------:|:-----:|:----:|:---------------:|
172
+ | 0.7691 | 0.0 | 1 | 0.7027 |
173
+ | 0.5556 | 0.05 | 135 | 0.5808 |
174
+ | 0.597 | 0.1 | 270 | 0.5488 |
175
+ | 0.5979 | 0.15 | 405 | 0.5277 |
176
+ | 0.4693 | 0.2 | 540 | 0.5108 |
177
+ | 0.5123 | 0.25 | 675 | 0.4978 |
178
+ | 0.4394 | 0.3 | 810 | 0.4883 |
179
+ | 0.46 | 0.35 | 945 | 0.4802 |
180
+ | 0.4472 | 0.4 | 1080 | 0.4748 |
181
+ | 0.47 | 0.45 | 1215 | 0.4687 |
182
+ | 0.4249 | 0.5 | 1350 | 0.4637 |
183
+ | 0.4823 | 0.55 | 1485 | 0.4599 |
184
+ | 0.4209 | 0.6 | 1620 | 0.4555 |
185
+ | 0.4909 | 0.65 | 1755 | 0.4517 |
186
+ | 0.4663 | 0.7 | 1890 | 0.4470 |
187
+ | 0.4215 | 0.75 | 2025 | 0.4437 |
188
+ | 0.4267 | 0.8 | 2160 | 0.4398 |
189
+ | 0.4109 | 0.85 | 2295 | 0.4364 |
190
+ | 0.4099 | 0.9 | 2430 | 0.4331 |
191
+ | 0.447 | 0.95 | 2565 | 0.4298 |
192
+ | 0.4412 | 1.0 | 2700 | 0.4272 |
193
+ | 0.3838 | 1.03 | 2835 | 0.4287 |
194
+ | 0.4262 | 1.08 | 2970 | 0.4274 |
195
+ | 0.3889 | 1.13 | 3105 | 0.4263 |
196
+ | 0.3114 | 1.18 | 3240 | 0.4255 |
197
+ | 0.3685 | 1.23 | 3375 | 0.4256 |
198
+ | 0.392 | 1.28 | 3510 | 0.4253 |
199
+ | 0.3751 | 1.33 | 3645 | 0.4255 |
200
+ | 0.3756 | 1.39 | 3780 | 0.4256 |
201
+ | 0.3108 | 1.44 | 3915 | 0.4258 |
202
+
203
+
204
+ ### Framework versions
205
+
206
+ - Transformers 4.37.0.dev0
207
+ - Pytorch 2.1.1+cu121
208
+ - Datasets 2.16.1
209
+ - Tokenizers 0.15.0
210
+ ## Training procedure
211
+
212
+
213
+ The following `bitsandbytes` quantization config was used during training:
214
+ - quant_method: bitsandbytes
215
+ - load_in_8bit: False
216
+ - load_in_4bit: True
217
+ - llm_int8_threshold: 6.0
218
+ - llm_int8_skip_modules: None
219
+ - llm_int8_enable_fp32_cpu_offload: False
220
+ - llm_int8_has_fp16_weight: False
221
+ - bnb_4bit_quant_type: nf4
222
+ - bnb_4bit_use_double_quant: True
223
+ - bnb_4bit_compute_dtype: bfloat16
224
+
225
+ ### Framework versions
226
+
227
+
228
+ - PEFT 0.6.0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
axolotl.config ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: rishiraj/CatPPT-base
2
+ model_type: MistralForCausalLM
3
+ tokenizer_type: LlamaTokenizer
4
+ is_mistral_derived_model: true
5
+
6
+ load_in_8bit: false
7
+ load_in_4bit: true
8
+ strict: false
9
+
10
+ model_config:
11
+ output_router_logits: true
12
+
13
+ datasets:
14
+ - path: teknium/openhermes
15
+ type: alpaca
16
+ prompt_style: chatml
17
+ - path: garage-bAInd/Open-Platypus
18
+ type: alpaca
19
+ prompt_style: chatml
20
+ - path: LDJnr/Capybara
21
+ type: sharegpt
22
+ conversation: chatml
23
+ - path: datasets/samantha-1.1.json
24
+ type: sharegpt
25
+ conversation: chatml
26
+ - path: datasets/grammarly-coedit-alpaca.jsonl
27
+ type: alpaca
28
+ prompt_style: chatml
29
+ - path: datasets/dolphin-coder-codegen.jsonl
30
+ type: alpaca_w_system.load_open_orca_chatml
31
+ - path: datasets/dolphin-coder-translate.jsonl
32
+ type: alpaca_w_system.load_open_orca_chatml
33
+ - path: datasets/data-evol_instruct-decontaminated-alpaca.jsonl
34
+ type: alpaca
35
+ prompt_style: chatml
36
+ - path: datasets/data-oss_instruct-decontaminated-alpaca.jsonl
37
+ type: alpaca
38
+ prompt_style: chatml
39
+ - path: jondurbin/airoboros-3.2
40
+ type: sharegpt
41
+ conversations: chatml
42
+ dataset_prepared_path: last_run_prepared
43
+ val_set_size: 0.01
44
+ output_dir: ./qlora-out-2
45
+ seed: 420
46
+
47
+ adapter: qlora
48
+ lora_model_dir:
49
+
50
+ sequence_len: 8192
51
+ sample_packing: true
52
+ pad_to_sequence_len: true
53
+
54
+ lora_r: 32
55
+ lora_alpha: 16
56
+ lora_dropout: 0.05
57
+ lora_target_modules:
58
+ lora_target_linear: true
59
+ lora_fan_in_fan_out:
60
+ lora_modules_to_save:
61
+ - embed_tokens
62
+ - lm_head
63
+
64
+ wandb_project:
65
+ wandb_entity:
66
+ wandb_watch:
67
+ wandb_name:
68
+ wandb_log_model:
69
+
70
+ gradient_accumulation_steps: 2
71
+ micro_batch_size: 3
72
+ num_epochs: 1.5
73
+ optimizer: paged_adamw_8bit
74
+ lr_scheduler: cosine
75
+ learning_rate: 0.0002
76
+
77
+ train_on_inputs: false
78
+ group_by_length: false
79
+ bf16: true
80
+ fp16: false
81
+ tf32: false
82
+
83
+ gradient_checkpointing: true
84
+ early_stopping_patience:
85
+ resume_from_checkpoint:
86
+ local_rank:
87
+ logging_steps: 1
88
+ xformers_attention:
89
+ flash_attention: true
90
+
91
+ loss_watchdog_threshold: 5.0
92
+ loss_watchdog_patience: 3
93
+
94
+ warmup_steps: 0
95
+ evals_per_epoch: 20
96
+ eval_table_size:
97
+ saves_per_epoch: 20
98
+ debug:
99
+ deepspeed:
100
+ weight_decay: 0.05
101
+ fsdp:
102
+ fsdp_config:
103
+ special_tokens:
104
+ bos_token: "<s>"
105
+ eos_token: "</s>"
106
+ unk_token: "<unk>"
107
+ eos_token: "<|im_end|>"
108
+ tokens:
109
+ - "<|im_start|>"
110
+ trust_remote_code: true
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": 32000,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "output_router_logits": true,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.37.0.dev0",
24
+ "use_cache": false,
25
+ "vocab_size": 32002
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.0.dev0"
6
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0641b6c2d327f4384a688b71fd8021a8d30e4fae20bf678e302f77ec9d34b941
3
+ size 4987229704
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804250db18d257cf0f2813a2ec621f939917a53e7cdd55b9214ec300c23b70c4
3
+ size 4899116440
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8643fddcadad54b169f48b794debce42d4e9b99d449d80813c41eb1c135c4a8
3
+ size 4999813120
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9d98377ea0b29783e74392eaaba4bd7322d269252a3ab2c0638034386c569a
3
+ size 4999813128
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2197675dd9657f43e89656ec3943879839b7dba23b82e6bbcb72e640f4cc5e30
3
+ size 4832007496
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b45c61859ecd5b822c3e081bad91d3f98b936b9d08b72802f3d74ce78a5ae71
3
+ size 4249047664
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28966993920
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
296
+ "model.norm.weight": "model-00006-of-00006.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|im_end|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "</s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<unk>",
48
+ "<s>",
49
+ "</s>"
50
+ ],
51
+ "bos_token": "<s>",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|im_end|>",
54
+ "legacy": true,
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "pad_token": "</s>",
57
+ "sp_model_kwargs": {},
58
+ "spaces_between_special_tokens": false,
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "trust_remote_code": true,
61
+ "unk_token": "<unk>",
62
+ "use_default_system_prompt": true,
63
+ "use_fast": true
64
+ }