titan087 commited on
Commit
311c0ef
1 Parent(s): bfe4b5c

Upload 16 files

Browse files
README.md ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ library_name: transformers
6
+ model-index:
7
+ - name: Rhea-72b-v0.5
8
+ results:
9
+ - task:
10
+ type: text-generation
11
+ name: Text Generation
12
+ dataset:
13
+ name: AI2 Reasoning Challenge (25-Shot)
14
+ type: ai2_arc
15
+ config: ARC-Challenge
16
+ split: test
17
+ args:
18
+ num_few_shot: 25
19
+ metrics:
20
+ - type: acc_norm
21
+ value: 79.78
22
+ name: normalized accuracy
23
+ source:
24
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5
25
+ name: Open LLM Leaderboard
26
+ - task:
27
+ type: text-generation
28
+ name: Text Generation
29
+ dataset:
30
+ name: HellaSwag (10-Shot)
31
+ type: hellaswag
32
+ split: validation
33
+ args:
34
+ num_few_shot: 10
35
+ metrics:
36
+ - type: acc_norm
37
+ value: 91.15
38
+ name: normalized accuracy
39
+ source:
40
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5
41
+ name: Open LLM Leaderboard
42
+ - task:
43
+ type: text-generation
44
+ name: Text Generation
45
+ dataset:
46
+ name: MMLU (5-Shot)
47
+ type: cais/mmlu
48
+ config: all
49
+ split: test
50
+ args:
51
+ num_few_shot: 5
52
+ metrics:
53
+ - type: acc
54
+ value: 77.95
55
+ name: accuracy
56
+ source:
57
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5
58
+ name: Open LLM Leaderboard
59
+ - task:
60
+ type: text-generation
61
+ name: Text Generation
62
+ dataset:
63
+ name: TruthfulQA (0-shot)
64
+ type: truthful_qa
65
+ config: multiple_choice
66
+ split: validation
67
+ args:
68
+ num_few_shot: 0
69
+ metrics:
70
+ - type: mc2
71
+ value: 74.5
72
+ source:
73
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5
74
+ name: Open LLM Leaderboard
75
+ - task:
76
+ type: text-generation
77
+ name: Text Generation
78
+ dataset:
79
+ name: Winogrande (5-shot)
80
+ type: winogrande
81
+ config: winogrande_xl
82
+ split: validation
83
+ args:
84
+ num_few_shot: 5
85
+ metrics:
86
+ - type: acc
87
+ value: 87.85
88
+ name: accuracy
89
+ source:
90
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5
91
+ name: Open LLM Leaderboard
92
+ - task:
93
+ type: text-generation
94
+ name: Text Generation
95
+ dataset:
96
+ name: GSM8k (5-shot)
97
+ type: gsm8k
98
+ config: main
99
+ split: test
100
+ args:
101
+ num_few_shot: 5
102
+ metrics:
103
+ - type: acc
104
+ value: 76.12
105
+ name: accuracy
106
+ source:
107
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5
108
+ name: Open LLM Leaderboard
109
+ ---
110
+ # Rhea-72b-v0.5
111
+
112
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64241c3d774cc340797429fc/97nXDuEhQUom3vaVcEvV-.jpeg)
113
+
114
+ The Rhea project is a project that conducts research on various learning methods to improve llm model performance. We fine-tuned the existing model using the [nox](https://github.com/davidkim205/nox) framework. We built a dataset for SFT learning based on the currently open dataset, and created a dataset using SGD (Self-Generated Dataset Creation Method for DPO Learning) for DPO learning.
115
+
116
+ Our model ranked first on HuggingFace's Open LLM leaderboard.
117
+
118
+
119
+ ## SGD : A Study on Self-Generated Dataset creation method for DPO Learning
120
+
121
+ This method proposes a novel method for generating datasets for DPO (Self-supervised Learning) models. We suggest a technique where sentences generated by the model are compared with the actual correct answers from an existing dataset, and sentences where the model's generated results do not match the correct answers are added. This enables the model to autonomously create training data, thereby enhancing the performance of DPO models.
122
+
123
+ ## Model Details
124
+
125
+ * **Model Developers** : davidkim(changyeon kim)
126
+ * **Repository** : [https://github.com/davidkim205/nox](https://github.com/davidkim205/nox)
127
+ * **base mode** : abacusai/Smaug-72B-v0.1
128
+ * **sft dataset** : datasets_enconv_4m
129
+ * **dpo dataset** : datasets_encomp_151k
130
+
131
+ ## sft dataset info : datasets_enconv_4m
132
+ ### 100k random shuffle datasets
133
+ - stack-exchange-preferences
134
+ - SlimOrca
135
+ - alpaca-gpt4
136
+ - SHP
137
+ - HC3
138
+ - databricks-dolly-15k
139
+ - orca-dpo-pairs
140
+ - us-stockname
141
+ - OpenHermes2.5-dpo-binarized-alpha
142
+ - distilabel-math-preference-dpo
143
+ - Neural-DPO
144
+ - truthy-dpo-v0.1
145
+ - distilabel-capybara-dpo-7k-binarized
146
+ - us-sentiment
147
+ - contextual-dpo-v0.1
148
+
149
+ ### 1k random shuffle datasets
150
+ - bigbench
151
+ - glue_mnli
152
+ - glue_qqp
153
+ - xnli
154
+ - codexglue_code2text_go
155
+ - trivia_qa
156
+ - medmcqa
157
+ - hendrycks_ethics
158
+ - super_glue_record
159
+ - glue_qnli
160
+ - anli_r3
161
+ - swag
162
+ - squad_v2
163
+ - nq_open
164
+ - drop
165
+ - glue_sst2
166
+ - blimp
167
+ - paws-x
168
+ - unscramble
169
+ - anli_r2
170
+ - babi
171
+ - math_qa
172
+ - social_i_qa
173
+ - piqa
174
+ - arithmetic
175
+ - anli_r1
176
+ - prost
177
+ - sciq
178
+ - mc_taco
179
+ - medqa
180
+ - super_glue_boolq
181
+ - hendrycks_math
182
+ - lambada
183
+ - toxigen-data
184
+ - glue_cola
185
+ - pubmed_qa
186
+ - logiqa
187
+ - mutual
188
+ - headqa
189
+ - bbh
190
+ - super_glue_wic
191
+ - openbookqa
192
+ - glue_mrpc
193
+ - web_questions
194
+ - qasper
195
+ - super_glue_multirc
196
+ - story_cloze
197
+ - super_glue_rte
198
+ - glue_rte
199
+ - race
200
+ - xwinograd
201
+ - asdiv
202
+ - xstory_cloze
203
+ - crows_pairs_multilingual
204
+ - belebele
205
+ - glue_wnli
206
+ - super_glue_wsc
207
+ - coqa
208
+ - super_glue_copa
209
+ - super_glue_cb
210
+ - winograd_wsc
211
+ - mgsm
212
+ - scrolls_contract_nli
213
+
214
+ * If the data set cannot be found, it is internal company data and cannot be made public.
215
+
216
+ ## dpo dataset info : datasets_encomp_151k
217
+ Randomly selecting data from each category within the training dataset, we constructed a DPO (Direct Preference Optimization) dataset using sentences with logits lower than the mean within the model-generated sentences.
218
+ * I'm sorry I can't reveal it.
219
+
220
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
221
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_davidkim205__Rhea-72b-v0.5)
222
+
223
+ | Metric |Value|
224
+ |---------------------------------|----:|
225
+ |Avg. |81.22|
226
+ |AI2 Reasoning Challenge (25-Shot)|79.78|
227
+ |HellaSwag (10-Shot) |91.15|
228
+ |MMLU (5-Shot) |77.95|
229
+ |TruthfulQA (0-shot) |74.50|
230
+ |Winogrande (5-shot) |87.85|
231
+ |GSM8k (5-shot) |76.12|
232
+
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./Rhea-72b-v0.5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 151643,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 24576,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 80,
18
+ "num_key_value_heads": 64,
19
+ "pad_token_id": 151643,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 1000000,
24
+ "seq_length": 32768,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.37.2",
28
+ "use_cache": true,
29
+ "vocab_size": 152064,
30
+ "quantization_config": {
31
+ "quant_method": "exl2",
32
+ "version": "0.0.18",
33
+ "bits": 4.0,
34
+ "head_bits": 6,
35
+ "calibration": {
36
+ "rows": 100,
37
+ "length": 2048,
38
+ "dataset": "(default)"
39
+ }
40
+ }
41
+ }
convert-to-safetensors.py ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ '''
2
+
3
+ Converts a transformers model to safetensors format and shards it.
4
+
5
+ This makes it faster to load (because of safetensors) and lowers its RAM usage
6
+ while loading (because of sharding).
7
+
8
+ Based on the original script by 81300:
9
+
10
+ https://gist.github.com/81300/fe5b08bff1cba45296a829b9d6b0f303
11
+
12
+ '''
13
+
14
+ import argparse
15
+ from pathlib import Path
16
+
17
+ import torch
18
+ from transformers import AutoModelForCausalLM, AutoTokenizer
19
+
20
+ parser = argparse.ArgumentParser(formatter_class=lambda prog: argparse.HelpFormatter(prog, max_help_position=54))
21
+ parser.add_argument('MODEL', type=str, default=None, nargs='?', help="Path to the input model.")
22
+ parser.add_argument('--output', type=str, default=None, help='Path to the output folder (default: models/{model_name}_safetensors).')
23
+ parser.add_argument("--max-shard-size", type=str, default="2GB", help="Maximum size of a shard in GB or MB (default: %(default)s).")
24
+ parser.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.')
25
+ args = parser.parse_args()
26
+
27
+ if __name__ == '__main__':
28
+ path = Path(args.MODEL)
29
+ model_name = path.name
30
+
31
+ print(f"Loading {model_name}...")
32
+ model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True, torch_dtype=torch.bfloat16 if args.bf16 else torch.float16)
33
+ tokenizer = AutoTokenizer.from_pretrained(path)
34
+
35
+ out_folder = args.output or Path(f"models/{model_name}_safetensors")
36
+ print(f"Saving the converted model to {out_folder} with a maximum shard size of {args.max_shard_size}...")
37
+ model.save_pretrained(out_folder, max_shard_size=args.max_shard_size, safe_serialization=True)
38
+ tokenizer.save_pretrained(out_folder)
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 151643,
4
+ "pad_token_id": 151643,
5
+ "transformers_version": "4.37.2"
6
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/davidkim205/Rhea-72b-v0.5
2
+ branch: main
3
+ download date: 2024-04-12 12:53:36
4
+ sha256sum:
5
+ 1552104d2964ab5498df478f06e8f2d12d8b740d0d1e86e573fa86e83370ea54 model-00001-of-00030.safetensors
6
+ c004efbdca6c27e0adeda703070440581133dbb276b524ebb660978aefb18b3d model-00002-of-00030.safetensors
7
+ eba7972f4f897776e1c0347af386fc7c0829e21c96a0dc4d6d62affa678f70c7 model-00003-of-00030.safetensors
8
+ 242c147d53a01d4ee356688b123f041dab202faa10a01ca8dfa91f3f1ab6b174 model-00004-of-00030.safetensors
9
+ 6850c40367b62c06dbc8e4a26beff5127ec4047ba6910199c1d2d5eb1885c1c3 model-00005-of-00030.safetensors
10
+ 6a70fd9919c79fa44241ff23506058846fb82466430dc90268e504425c9087c0 model-00006-of-00030.safetensors
11
+ d08e7436a290f3cff1dfbb123dead6e959ee910cddaf9b9019167f66417c888e model-00007-of-00030.safetensors
12
+ b1ebebedf15e76ef25147cabbf5bd81f89e994156a7ceba1d2dda0f4d1d9b48a model-00008-of-00030.safetensors
13
+ d288f81f5a8a00f37823f1e5a3662bf7013138b64267fa8d691fec2bb6db5095 model-00009-of-00030.safetensors
14
+ 8f7174d0dd4d10a9367f914c4f569348bfdb1dcf66a35061fe3cab782306f9f0 model-00010-of-00030.safetensors
15
+ e2c636deaeb15d8560d1b032fb71f264ca123da835121d1654dd3114bef2da24 model-00011-of-00030.safetensors
16
+ 680e1ad6a16adac3d587cbf3640d630878aeb5d32ae161c2bc3d2ad9a7736a32 model-00012-of-00030.safetensors
17
+ df2786be9ed100f670b22bae746e3f38593795e520dec52eae72e0e14d23608a model-00013-of-00030.safetensors
18
+ 9d866cd5b9e96f6bfbea726575e711faa5d7d8e9c95fdb6131eb56d4d0fc96a7 model-00014-of-00030.safetensors
19
+ 113cdaafac7651c3562968a76df790f4e947753992f8baadd30f59f0499102af model-00015-of-00030.safetensors
20
+ 6893854c7dd991b7c16917a612b533a630a12ac5eb529854858ec50af3af0923 model-00016-of-00030.safetensors
21
+ d2d4dbaff961611d0fa042f99d3dfb2a9a7b212d7b340f464ea414c955c25a4c model-00017-of-00030.safetensors
22
+ 7bc26ee172c4280a168cc3c647571e0bd70312e5691f1b3ba3e58a0f7d55eec8 model-00018-of-00030.safetensors
23
+ bcb796cfe4e4cc22a7ae4bba7787b106904d51412f205184f49a5436a259a0c1 model-00019-of-00030.safetensors
24
+ 11fefcc7fcf660ba781555c1e03485f17240b8c33f1c31f698fecdb046db79ad model-00020-of-00030.safetensors
25
+ d091b34d5194838387bf2e68ad9c3de0eca9f54e6b32b9f3fdd7da835d801bfc model-00021-of-00030.safetensors
26
+ 5a8f357f229a792e2e9bdceb9c1d4c1c5d5a6f3b9f3d1c64251f299c6102cb3a model-00022-of-00030.safetensors
27
+ c56f1e00f68706e3db58d19ebfc0130fb0490986dafbb99958bd595befd2db75 model-00023-of-00030.safetensors
28
+ 295edcef14d0d3bf0e5b8b36497cb124b6543be1c519fc40e5826d28c8c9307d model-00024-of-00030.safetensors
29
+ aed568f895b801321c8f064eee6cf3344c999440e76aa4eb643d0f6c60ffe0b5 model-00025-of-00030.safetensors
30
+ 34701969b7ea02b95e9706b4cfff0517358262f1c8d504d4173ad1e2d03c6da4 model-00026-of-00030.safetensors
31
+ d74d457cd4e05375a4ccdbda38875bc2546b7e6f7a67f3426dbdaaf7945d96e7 model-00027-of-00030.safetensors
32
+ e74e1e492630fafcd6b96c7cf56754136f24fa9db9a05a21ea661da9e576a222 model-00028-of-00030.safetensors
33
+ 0ca00020579070694301f7cb555d4f57055b70a1542b490d75ffe0a9ad40399b model-00029-of-00030.safetensors
34
+ 79610bd5d36c24104cb34d824b568262371b322edb79f9e4e0dfa9d61ff31e84 model-00030-of-00030.safetensors
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1,1050 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 144577150976
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00030-of-00030.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00030.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00030.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
15
+ "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00030.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00030.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00030.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00030.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
28
+ "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00030.safetensors",
29
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
30
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00030.safetensors",
31
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
32
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00030.safetensors",
33
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
34
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
35
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
36
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
37
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
38
+ "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
39
+ "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00030.safetensors",
40
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
41
+ "model.layers.10.self_attn.o_proj.bias": "model-00005-of-00030.safetensors",
42
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
43
+ "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00030.safetensors",
44
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
45
+ "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00030.safetensors",
46
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
47
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
48
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
49
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
50
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
51
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
52
+ "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00030.safetensors",
53
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
54
+ "model.layers.11.self_attn.o_proj.bias": "model-00005-of-00030.safetensors",
55
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
56
+ "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00030.safetensors",
57
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
58
+ "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00030.safetensors",
59
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
60
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors",
61
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
62
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
63
+ "model.layers.12.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
64
+ "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
65
+ "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00030.safetensors",
66
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
67
+ "model.layers.12.self_attn.o_proj.bias": "model-00005-of-00030.safetensors",
68
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
69
+ "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00030.safetensors",
70
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
71
+ "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00030.safetensors",
72
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
73
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
74
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
75
+ "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
76
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
77
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
78
+ "model.layers.13.self_attn.k_proj.bias": "model-00006-of-00030.safetensors",
79
+ "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
80
+ "model.layers.13.self_attn.o_proj.bias": "model-00006-of-00030.safetensors",
81
+ "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
82
+ "model.layers.13.self_attn.q_proj.bias": "model-00006-of-00030.safetensors",
83
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
84
+ "model.layers.13.self_attn.v_proj.bias": "model-00006-of-00030.safetensors",
85
+ "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
86
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
87
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
88
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
89
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
90
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
91
+ "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00030.safetensors",
92
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
93
+ "model.layers.14.self_attn.o_proj.bias": "model-00006-of-00030.safetensors",
94
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
95
+ "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00030.safetensors",
96
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
97
+ "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00030.safetensors",
98
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
99
+ "model.layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors",
100
+ "model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
101
+ "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
102
+ "model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
103
+ "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
104
+ "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00030.safetensors",
105
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
106
+ "model.layers.15.self_attn.o_proj.bias": "model-00006-of-00030.safetensors",
107
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
108
+ "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00030.safetensors",
109
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
110
+ "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00030.safetensors",
111
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
112
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
113
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
114
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
115
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
116
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
117
+ "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00030.safetensors",
118
+ "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
119
+ "model.layers.16.self_attn.o_proj.bias": "model-00007-of-00030.safetensors",
120
+ "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
121
+ "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00030.safetensors",
122
+ "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
123
+ "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00030.safetensors",
124
+ "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
125
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
126
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
127
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
128
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
129
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
130
+ "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00030.safetensors",
131
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
132
+ "model.layers.17.self_attn.o_proj.bias": "model-00007-of-00030.safetensors",
133
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
134
+ "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00030.safetensors",
135
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
136
+ "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00030.safetensors",
137
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
138
+ "model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors",
139
+ "model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
140
+ "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
141
+ "model.layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
142
+ "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
143
+ "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00030.safetensors",
144
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
145
+ "model.layers.18.self_attn.o_proj.bias": "model-00008-of-00030.safetensors",
146
+ "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
147
+ "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00030.safetensors",
148
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
149
+ "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00030.safetensors",
150
+ "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
151
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
152
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
153
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
154
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
155
+ "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
156
+ "model.layers.19.self_attn.k_proj.bias": "model-00008-of-00030.safetensors",
157
+ "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
158
+ "model.layers.19.self_attn.o_proj.bias": "model-00008-of-00030.safetensors",
159
+ "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
160
+ "model.layers.19.self_attn.q_proj.bias": "model-00008-of-00030.safetensors",
161
+ "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
162
+ "model.layers.19.self_attn.v_proj.bias": "model-00008-of-00030.safetensors",
163
+ "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
164
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
165
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
166
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
167
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
168
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
169
+ "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00030.safetensors",
170
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
171
+ "model.layers.2.self_attn.o_proj.bias": "model-00002-of-00030.safetensors",
172
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
173
+ "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00030.safetensors",
174
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
175
+ "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00030.safetensors",
176
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
177
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
178
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
179
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
180
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
181
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
182
+ "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00030.safetensors",
183
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
184
+ "model.layers.20.self_attn.o_proj.bias": "model-00008-of-00030.safetensors",
185
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
186
+ "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00030.safetensors",
187
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
188
+ "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00030.safetensors",
189
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
190
+ "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
191
+ "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
192
+ "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
193
+ "model.layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
194
+ "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
195
+ "model.layers.21.self_attn.k_proj.bias": "model-00009-of-00030.safetensors",
196
+ "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
197
+ "model.layers.21.self_attn.o_proj.bias": "model-00009-of-00030.safetensors",
198
+ "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
199
+ "model.layers.21.self_attn.q_proj.bias": "model-00009-of-00030.safetensors",
200
+ "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
201
+ "model.layers.21.self_attn.v_proj.bias": "model-00009-of-00030.safetensors",
202
+ "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
203
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
204
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
205
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
206
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
207
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
208
+ "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00030.safetensors",
209
+ "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
210
+ "model.layers.22.self_attn.o_proj.bias": "model-00009-of-00030.safetensors",
211
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
212
+ "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00030.safetensors",
213
+ "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
214
+ "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00030.safetensors",
215
+ "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
216
+ "model.layers.23.input_layernorm.weight": "model-00010-of-00030.safetensors",
217
+ "model.layers.23.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
218
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
219
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
220
+ "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
221
+ "model.layers.23.self_attn.k_proj.bias": "model-00009-of-00030.safetensors",
222
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
223
+ "model.layers.23.self_attn.o_proj.bias": "model-00009-of-00030.safetensors",
224
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
225
+ "model.layers.23.self_attn.q_proj.bias": "model-00009-of-00030.safetensors",
226
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
227
+ "model.layers.23.self_attn.v_proj.bias": "model-00009-of-00030.safetensors",
228
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
229
+ "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
230
+ "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
231
+ "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
232
+ "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
233
+ "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
234
+ "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00030.safetensors",
235
+ "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
236
+ "model.layers.24.self_attn.o_proj.bias": "model-00010-of-00030.safetensors",
237
+ "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
238
+ "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00030.safetensors",
239
+ "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
240
+ "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00030.safetensors",
241
+ "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
242
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
243
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
244
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
245
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
246
+ "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
247
+ "model.layers.25.self_attn.k_proj.bias": "model-00010-of-00030.safetensors",
248
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
249
+ "model.layers.25.self_attn.o_proj.bias": "model-00010-of-00030.safetensors",
250
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
251
+ "model.layers.25.self_attn.q_proj.bias": "model-00010-of-00030.safetensors",
252
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
253
+ "model.layers.25.self_attn.v_proj.bias": "model-00010-of-00030.safetensors",
254
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
255
+ "model.layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors",
256
+ "model.layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
257
+ "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
258
+ "model.layers.26.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
259
+ "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
260
+ "model.layers.26.self_attn.k_proj.bias": "model-00010-of-00030.safetensors",
261
+ "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
262
+ "model.layers.26.self_attn.o_proj.bias": "model-00010-of-00030.safetensors",
263
+ "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
264
+ "model.layers.26.self_attn.q_proj.bias": "model-00010-of-00030.safetensors",
265
+ "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
266
+ "model.layers.26.self_attn.v_proj.bias": "model-00010-of-00030.safetensors",
267
+ "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
268
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
269
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
270
+ "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
271
+ "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
272
+ "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
273
+ "model.layers.27.self_attn.k_proj.bias": "model-00011-of-00030.safetensors",
274
+ "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
275
+ "model.layers.27.self_attn.o_proj.bias": "model-00011-of-00030.safetensors",
276
+ "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
277
+ "model.layers.27.self_attn.q_proj.bias": "model-00011-of-00030.safetensors",
278
+ "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
279
+ "model.layers.27.self_attn.v_proj.bias": "model-00011-of-00030.safetensors",
280
+ "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
281
+ "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
282
+ "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
283
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
284
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
285
+ "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
286
+ "model.layers.28.self_attn.k_proj.bias": "model-00011-of-00030.safetensors",
287
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
288
+ "model.layers.28.self_attn.o_proj.bias": "model-00011-of-00030.safetensors",
289
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
290
+ "model.layers.28.self_attn.q_proj.bias": "model-00011-of-00030.safetensors",
291
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
292
+ "model.layers.28.self_attn.v_proj.bias": "model-00011-of-00030.safetensors",
293
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
294
+ "model.layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors",
295
+ "model.layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
296
+ "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
297
+ "model.layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
298
+ "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
299
+ "model.layers.29.self_attn.k_proj.bias": "model-00011-of-00030.safetensors",
300
+ "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
301
+ "model.layers.29.self_attn.o_proj.bias": "model-00011-of-00030.safetensors",
302
+ "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
303
+ "model.layers.29.self_attn.q_proj.bias": "model-00011-of-00030.safetensors",
304
+ "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
305
+ "model.layers.29.self_attn.v_proj.bias": "model-00011-of-00030.safetensors",
306
+ "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
307
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
308
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
309
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
310
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
311
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
312
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00030.safetensors",
313
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
314
+ "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00030.safetensors",
315
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
316
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00030.safetensors",
317
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
318
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00030.safetensors",
319
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
320
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
321
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
322
+ "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
323
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
324
+ "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
325
+ "model.layers.30.self_attn.k_proj.bias": "model-00012-of-00030.safetensors",
326
+ "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
327
+ "model.layers.30.self_attn.o_proj.bias": "model-00012-of-00030.safetensors",
328
+ "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
329
+ "model.layers.30.self_attn.q_proj.bias": "model-00012-of-00030.safetensors",
330
+ "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
331
+ "model.layers.30.self_attn.v_proj.bias": "model-00012-of-00030.safetensors",
332
+ "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
333
+ "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
334
+ "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
335
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
336
+ "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
337
+ "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
338
+ "model.layers.31.self_attn.k_proj.bias": "model-00012-of-00030.safetensors",
339
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
340
+ "model.layers.31.self_attn.o_proj.bias": "model-00012-of-00030.safetensors",
341
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
342
+ "model.layers.31.self_attn.q_proj.bias": "model-00012-of-00030.safetensors",
343
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
344
+ "model.layers.31.self_attn.v_proj.bias": "model-00012-of-00030.safetensors",
345
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
346
+ "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
347
+ "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
348
+ "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
349
+ "model.layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
350
+ "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
351
+ "model.layers.32.self_attn.k_proj.bias": "model-00012-of-00030.safetensors",
352
+ "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
353
+ "model.layers.32.self_attn.o_proj.bias": "model-00013-of-00030.safetensors",
354
+ "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
355
+ "model.layers.32.self_attn.q_proj.bias": "model-00012-of-00030.safetensors",
356
+ "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
357
+ "model.layers.32.self_attn.v_proj.bias": "model-00013-of-00030.safetensors",
358
+ "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
359
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
360
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
361
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
362
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
363
+ "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
364
+ "model.layers.33.self_attn.k_proj.bias": "model-00013-of-00030.safetensors",
365
+ "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
366
+ "model.layers.33.self_attn.o_proj.bias": "model-00013-of-00030.safetensors",
367
+ "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
368
+ "model.layers.33.self_attn.q_proj.bias": "model-00013-of-00030.safetensors",
369
+ "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
370
+ "model.layers.33.self_attn.v_proj.bias": "model-00013-of-00030.safetensors",
371
+ "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
372
+ "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
373
+ "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
374
+ "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
375
+ "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
376
+ "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
377
+ "model.layers.34.self_attn.k_proj.bias": "model-00013-of-00030.safetensors",
378
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
379
+ "model.layers.34.self_attn.o_proj.bias": "model-00013-of-00030.safetensors",
380
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
381
+ "model.layers.34.self_attn.q_proj.bias": "model-00013-of-00030.safetensors",
382
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
383
+ "model.layers.34.self_attn.v_proj.bias": "model-00013-of-00030.safetensors",
384
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
385
+ "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
386
+ "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
387
+ "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
388
+ "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
389
+ "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
390
+ "model.layers.35.self_attn.k_proj.bias": "model-00014-of-00030.safetensors",
391
+ "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
392
+ "model.layers.35.self_attn.o_proj.bias": "model-00014-of-00030.safetensors",
393
+ "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
394
+ "model.layers.35.self_attn.q_proj.bias": "model-00014-of-00030.safetensors",
395
+ "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
396
+ "model.layers.35.self_attn.v_proj.bias": "model-00014-of-00030.safetensors",
397
+ "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
398
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
399
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
400
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
401
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
402
+ "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
403
+ "model.layers.36.self_attn.k_proj.bias": "model-00014-of-00030.safetensors",
404
+ "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
405
+ "model.layers.36.self_attn.o_proj.bias": "model-00014-of-00030.safetensors",
406
+ "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
407
+ "model.layers.36.self_attn.q_proj.bias": "model-00014-of-00030.safetensors",
408
+ "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
409
+ "model.layers.36.self_attn.v_proj.bias": "model-00014-of-00030.safetensors",
410
+ "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
411
+ "model.layers.37.input_layernorm.weight": "model-00015-of-00030.safetensors",
412
+ "model.layers.37.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
413
+ "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
414
+ "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
415
+ "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
416
+ "model.layers.37.self_attn.k_proj.bias": "model-00014-of-00030.safetensors",
417
+ "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
418
+ "model.layers.37.self_attn.o_proj.bias": "model-00014-of-00030.safetensors",
419
+ "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
420
+ "model.layers.37.self_attn.q_proj.bias": "model-00014-of-00030.safetensors",
421
+ "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
422
+ "model.layers.37.self_attn.v_proj.bias": "model-00014-of-00030.safetensors",
423
+ "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
424
+ "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
425
+ "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
426
+ "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
427
+ "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
428
+ "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
429
+ "model.layers.38.self_attn.k_proj.bias": "model-00015-of-00030.safetensors",
430
+ "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
431
+ "model.layers.38.self_attn.o_proj.bias": "model-00015-of-00030.safetensors",
432
+ "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
433
+ "model.layers.38.self_attn.q_proj.bias": "model-00015-of-00030.safetensors",
434
+ "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
435
+ "model.layers.38.self_attn.v_proj.bias": "model-00015-of-00030.safetensors",
436
+ "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
437
+ "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
438
+ "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
439
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
440
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
441
+ "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
442
+ "model.layers.39.self_attn.k_proj.bias": "model-00015-of-00030.safetensors",
443
+ "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
444
+ "model.layers.39.self_attn.o_proj.bias": "model-00015-of-00030.safetensors",
445
+ "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
446
+ "model.layers.39.self_attn.q_proj.bias": "model-00015-of-00030.safetensors",
447
+ "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
448
+ "model.layers.39.self_attn.v_proj.bias": "model-00015-of-00030.safetensors",
449
+ "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
450
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors",
451
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
452
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
453
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
454
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
455
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00030.safetensors",
456
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
457
+ "model.layers.4.self_attn.o_proj.bias": "model-00003-of-00030.safetensors",
458
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
459
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00030.safetensors",
460
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
461
+ "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00030.safetensors",
462
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
463
+ "model.layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors",
464
+ "model.layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
465
+ "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
466
+ "model.layers.40.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
467
+ "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
468
+ "model.layers.40.self_attn.k_proj.bias": "model-00015-of-00030.safetensors",
469
+ "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
470
+ "model.layers.40.self_attn.o_proj.bias": "model-00015-of-00030.safetensors",
471
+ "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
472
+ "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00030.safetensors",
473
+ "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
474
+ "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00030.safetensors",
475
+ "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
476
+ "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
477
+ "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
478
+ "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
479
+ "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
480
+ "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
481
+ "model.layers.41.self_attn.k_proj.bias": "model-00016-of-00030.safetensors",
482
+ "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
483
+ "model.layers.41.self_attn.o_proj.bias": "model-00016-of-00030.safetensors",
484
+ "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
485
+ "model.layers.41.self_attn.q_proj.bias": "model-00016-of-00030.safetensors",
486
+ "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
487
+ "model.layers.41.self_attn.v_proj.bias": "model-00016-of-00030.safetensors",
488
+ "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
489
+ "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
490
+ "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
491
+ "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
492
+ "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
493
+ "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
494
+ "model.layers.42.self_attn.k_proj.bias": "model-00016-of-00030.safetensors",
495
+ "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
496
+ "model.layers.42.self_attn.o_proj.bias": "model-00016-of-00030.safetensors",
497
+ "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
498
+ "model.layers.42.self_attn.q_proj.bias": "model-00016-of-00030.safetensors",
499
+ "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
500
+ "model.layers.42.self_attn.v_proj.bias": "model-00016-of-00030.safetensors",
501
+ "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
502
+ "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
503
+ "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
504
+ "model.layers.43.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
505
+ "model.layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
506
+ "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
507
+ "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00030.safetensors",
508
+ "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
509
+ "model.layers.43.self_attn.o_proj.bias": "model-00016-of-00030.safetensors",
510
+ "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
511
+ "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00030.safetensors",
512
+ "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
513
+ "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00030.safetensors",
514
+ "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
515
+ "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
516
+ "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
517
+ "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
518
+ "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
519
+ "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
520
+ "model.layers.44.self_attn.k_proj.bias": "model-00017-of-00030.safetensors",
521
+ "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
522
+ "model.layers.44.self_attn.o_proj.bias": "model-00017-of-00030.safetensors",
523
+ "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
524
+ "model.layers.44.self_attn.q_proj.bias": "model-00017-of-00030.safetensors",
525
+ "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
526
+ "model.layers.44.self_attn.v_proj.bias": "model-00017-of-00030.safetensors",
527
+ "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
528
+ "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
529
+ "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
530
+ "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
531
+ "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
532
+ "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
533
+ "model.layers.45.self_attn.k_proj.bias": "model-00017-of-00030.safetensors",
534
+ "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
535
+ "model.layers.45.self_attn.o_proj.bias": "model-00017-of-00030.safetensors",
536
+ "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
537
+ "model.layers.45.self_attn.q_proj.bias": "model-00017-of-00030.safetensors",
538
+ "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
539
+ "model.layers.45.self_attn.v_proj.bias": "model-00017-of-00030.safetensors",
540
+ "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
541
+ "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
542
+ "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
543
+ "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
544
+ "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
545
+ "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
546
+ "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00030.safetensors",
547
+ "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
548
+ "model.layers.46.self_attn.o_proj.bias": "model-00018-of-00030.safetensors",
549
+ "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
550
+ "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00030.safetensors",
551
+ "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
552
+ "model.layers.46.self_attn.v_proj.bias": "model-00018-of-00030.safetensors",
553
+ "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
554
+ "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
555
+ "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
556
+ "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
557
+ "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
558
+ "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
559
+ "model.layers.47.self_attn.k_proj.bias": "model-00018-of-00030.safetensors",
560
+ "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
561
+ "model.layers.47.self_attn.o_proj.bias": "model-00018-of-00030.safetensors",
562
+ "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
563
+ "model.layers.47.self_attn.q_proj.bias": "model-00018-of-00030.safetensors",
564
+ "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
565
+ "model.layers.47.self_attn.v_proj.bias": "model-00018-of-00030.safetensors",
566
+ "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
567
+ "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
568
+ "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
569
+ "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
570
+ "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
571
+ "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
572
+ "model.layers.48.self_attn.k_proj.bias": "model-00018-of-00030.safetensors",
573
+ "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
574
+ "model.layers.48.self_attn.o_proj.bias": "model-00018-of-00030.safetensors",
575
+ "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
576
+ "model.layers.48.self_attn.q_proj.bias": "model-00018-of-00030.safetensors",
577
+ "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
578
+ "model.layers.48.self_attn.v_proj.bias": "model-00018-of-00030.safetensors",
579
+ "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
580
+ "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
581
+ "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
582
+ "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
583
+ "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
584
+ "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
585
+ "model.layers.49.self_attn.k_proj.bias": "model-00019-of-00030.safetensors",
586
+ "model.layers.49.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
587
+ "model.layers.49.self_attn.o_proj.bias": "model-00019-of-00030.safetensors",
588
+ "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
589
+ "model.layers.49.self_attn.q_proj.bias": "model-00019-of-00030.safetensors",
590
+ "model.layers.49.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
591
+ "model.layers.49.self_attn.v_proj.bias": "model-00019-of-00030.safetensors",
592
+ "model.layers.49.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
593
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
594
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
595
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
596
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
597
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
598
+ "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00030.safetensors",
599
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
600
+ "model.layers.5.self_attn.o_proj.bias": "model-00003-of-00030.safetensors",
601
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
602
+ "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00030.safetensors",
603
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
604
+ "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00030.safetensors",
605
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
606
+ "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
607
+ "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
608
+ "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
609
+ "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
610
+ "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
611
+ "model.layers.50.self_attn.k_proj.bias": "model-00019-of-00030.safetensors",
612
+ "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
613
+ "model.layers.50.self_attn.o_proj.bias": "model-00019-of-00030.safetensors",
614
+ "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
615
+ "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00030.safetensors",
616
+ "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
617
+ "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00030.safetensors",
618
+ "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
619
+ "model.layers.51.input_layernorm.weight": "model-00020-of-00030.safetensors",
620
+ "model.layers.51.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
621
+ "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
622
+ "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
623
+ "model.layers.51.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
624
+ "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00030.safetensors",
625
+ "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
626
+ "model.layers.51.self_attn.o_proj.bias": "model-00019-of-00030.safetensors",
627
+ "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
628
+ "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00030.safetensors",
629
+ "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
630
+ "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00030.safetensors",
631
+ "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
632
+ "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
633
+ "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
634
+ "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
635
+ "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
636
+ "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
637
+ "model.layers.52.self_attn.k_proj.bias": "model-00020-of-00030.safetensors",
638
+ "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
639
+ "model.layers.52.self_attn.o_proj.bias": "model-00020-of-00030.safetensors",
640
+ "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
641
+ "model.layers.52.self_attn.q_proj.bias": "model-00020-of-00030.safetensors",
642
+ "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
643
+ "model.layers.52.self_attn.v_proj.bias": "model-00020-of-00030.safetensors",
644
+ "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
645
+ "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
646
+ "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
647
+ "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
648
+ "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
649
+ "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
650
+ "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00030.safetensors",
651
+ "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
652
+ "model.layers.53.self_attn.o_proj.bias": "model-00020-of-00030.safetensors",
653
+ "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
654
+ "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00030.safetensors",
655
+ "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
656
+ "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00030.safetensors",
657
+ "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
658
+ "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
659
+ "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
660
+ "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
661
+ "model.layers.54.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
662
+ "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
663
+ "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00030.safetensors",
664
+ "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
665
+ "model.layers.54.self_attn.o_proj.bias": "model-00020-of-00030.safetensors",
666
+ "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
667
+ "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00030.safetensors",
668
+ "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
669
+ "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00030.safetensors",
670
+ "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
671
+ "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
672
+ "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
673
+ "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
674
+ "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
675
+ "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
676
+ "model.layers.55.self_attn.k_proj.bias": "model-00021-of-00030.safetensors",
677
+ "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
678
+ "model.layers.55.self_attn.o_proj.bias": "model-00021-of-00030.safetensors",
679
+ "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
680
+ "model.layers.55.self_attn.q_proj.bias": "model-00021-of-00030.safetensors",
681
+ "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
682
+ "model.layers.55.self_attn.v_proj.bias": "model-00021-of-00030.safetensors",
683
+ "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
684
+ "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
685
+ "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
686
+ "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
687
+ "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
688
+ "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
689
+ "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00030.safetensors",
690
+ "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
691
+ "model.layers.56.self_attn.o_proj.bias": "model-00021-of-00030.safetensors",
692
+ "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
693
+ "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00030.safetensors",
694
+ "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
695
+ "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00030.safetensors",
696
+ "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
697
+ "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
698
+ "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
699
+ "model.layers.57.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
700
+ "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
701
+ "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
702
+ "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00030.safetensors",
703
+ "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
704
+ "model.layers.57.self_attn.o_proj.bias": "model-00021-of-00030.safetensors",
705
+ "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
706
+ "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00030.safetensors",
707
+ "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
708
+ "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00030.safetensors",
709
+ "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
710
+ "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
711
+ "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
712
+ "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
713
+ "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
714
+ "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
715
+ "model.layers.58.self_attn.k_proj.bias": "model-00022-of-00030.safetensors",
716
+ "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
717
+ "model.layers.58.self_attn.o_proj.bias": "model-00022-of-00030.safetensors",
718
+ "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
719
+ "model.layers.58.self_attn.q_proj.bias": "model-00022-of-00030.safetensors",
720
+ "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
721
+ "model.layers.58.self_attn.v_proj.bias": "model-00022-of-00030.safetensors",
722
+ "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
723
+ "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
724
+ "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
725
+ "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
726
+ "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
727
+ "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
728
+ "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00030.safetensors",
729
+ "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
730
+ "model.layers.59.self_attn.o_proj.bias": "model-00022-of-00030.safetensors",
731
+ "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
732
+ "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00030.safetensors",
733
+ "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
734
+ "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00030.safetensors",
735
+ "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
736
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
737
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
738
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
739
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
740
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
741
+ "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00030.safetensors",
742
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
743
+ "model.layers.6.self_attn.o_proj.bias": "model-00003-of-00030.safetensors",
744
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
745
+ "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00030.safetensors",
746
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
747
+ "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00030.safetensors",
748
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
749
+ "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
750
+ "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
751
+ "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
752
+ "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
753
+ "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
754
+ "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00030.safetensors",
755
+ "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
756
+ "model.layers.60.self_attn.o_proj.bias": "model-00023-of-00030.safetensors",
757
+ "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
758
+ "model.layers.60.self_attn.q_proj.bias": "model-00022-of-00030.safetensors",
759
+ "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
760
+ "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00030.safetensors",
761
+ "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
762
+ "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
763
+ "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
764
+ "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
765
+ "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
766
+ "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
767
+ "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00030.safetensors",
768
+ "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
769
+ "model.layers.61.self_attn.o_proj.bias": "model-00023-of-00030.safetensors",
770
+ "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
771
+ "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00030.safetensors",
772
+ "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
773
+ "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00030.safetensors",
774
+ "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
775
+ "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
776
+ "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
777
+ "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
778
+ "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
779
+ "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
780
+ "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00030.safetensors",
781
+ "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
782
+ "model.layers.62.self_attn.o_proj.bias": "model-00023-of-00030.safetensors",
783
+ "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
784
+ "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00030.safetensors",
785
+ "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
786
+ "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00030.safetensors",
787
+ "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
788
+ "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
789
+ "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
790
+ "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
791
+ "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
792
+ "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
793
+ "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00030.safetensors",
794
+ "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
795
+ "model.layers.63.self_attn.o_proj.bias": "model-00024-of-00030.safetensors",
796
+ "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
797
+ "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00030.safetensors",
798
+ "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
799
+ "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00030.safetensors",
800
+ "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
801
+ "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
802
+ "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
803
+ "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
804
+ "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
805
+ "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
806
+ "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00030.safetensors",
807
+ "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
808
+ "model.layers.64.self_attn.o_proj.bias": "model-00024-of-00030.safetensors",
809
+ "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
810
+ "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00030.safetensors",
811
+ "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
812
+ "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00030.safetensors",
813
+ "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
814
+ "model.layers.65.input_layernorm.weight": "model-00025-of-00030.safetensors",
815
+ "model.layers.65.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
816
+ "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
817
+ "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
818
+ "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
819
+ "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00030.safetensors",
820
+ "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
821
+ "model.layers.65.self_attn.o_proj.bias": "model-00024-of-00030.safetensors",
822
+ "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
823
+ "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00030.safetensors",
824
+ "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
825
+ "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00030.safetensors",
826
+ "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
827
+ "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
828
+ "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
829
+ "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
830
+ "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
831
+ "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
832
+ "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00030.safetensors",
833
+ "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
834
+ "model.layers.66.self_attn.o_proj.bias": "model-00025-of-00030.safetensors",
835
+ "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
836
+ "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00030.safetensors",
837
+ "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
838
+ "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00030.safetensors",
839
+ "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
840
+ "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
841
+ "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
842
+ "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
843
+ "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
844
+ "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
845
+ "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00030.safetensors",
846
+ "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
847
+ "model.layers.67.self_attn.o_proj.bias": "model-00025-of-00030.safetensors",
848
+ "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
849
+ "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00030.safetensors",
850
+ "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
851
+ "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00030.safetensors",
852
+ "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
853
+ "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
854
+ "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
855
+ "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
856
+ "model.layers.68.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
857
+ "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
858
+ "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00030.safetensors",
859
+ "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
860
+ "model.layers.68.self_attn.o_proj.bias": "model-00025-of-00030.safetensors",
861
+ "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
862
+ "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00030.safetensors",
863
+ "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
864
+ "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00030.safetensors",
865
+ "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
866
+ "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
867
+ "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
868
+ "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
869
+ "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
870
+ "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
871
+ "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00030.safetensors",
872
+ "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
873
+ "model.layers.69.self_attn.o_proj.bias": "model-00026-of-00030.safetensors",
874
+ "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
875
+ "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00030.safetensors",
876
+ "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
877
+ "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00030.safetensors",
878
+ "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
879
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors",
880
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
881
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
882
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
883
+ "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
884
+ "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00030.safetensors",
885
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
886
+ "model.layers.7.self_attn.o_proj.bias": "model-00004-of-00030.safetensors",
887
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
888
+ "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00030.safetensors",
889
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
890
+ "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00030.safetensors",
891
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
892
+ "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
893
+ "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
894
+ "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
895
+ "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
896
+ "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
897
+ "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00030.safetensors",
898
+ "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
899
+ "model.layers.70.self_attn.o_proj.bias": "model-00026-of-00030.safetensors",
900
+ "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
901
+ "model.layers.70.self_attn.q_proj.bias": "model-00026-of-00030.safetensors",
902
+ "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
903
+ "model.layers.70.self_attn.v_proj.bias": "model-00026-of-00030.safetensors",
904
+ "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
905
+ "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
906
+ "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
907
+ "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
908
+ "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
909
+ "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
910
+ "model.layers.71.self_attn.k_proj.bias": "model-00026-of-00030.safetensors",
911
+ "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
912
+ "model.layers.71.self_attn.o_proj.bias": "model-00026-of-00030.safetensors",
913
+ "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
914
+ "model.layers.71.self_attn.q_proj.bias": "model-00026-of-00030.safetensors",
915
+ "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
916
+ "model.layers.71.self_attn.v_proj.bias": "model-00026-of-00030.safetensors",
917
+ "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
918
+ "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
919
+ "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
920
+ "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
921
+ "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
922
+ "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
923
+ "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00030.safetensors",
924
+ "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
925
+ "model.layers.72.self_attn.o_proj.bias": "model-00027-of-00030.safetensors",
926
+ "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
927
+ "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00030.safetensors",
928
+ "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
929
+ "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00030.safetensors",
930
+ "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
931
+ "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
932
+ "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
933
+ "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
934
+ "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
935
+ "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
936
+ "model.layers.73.self_attn.k_proj.bias": "model-00027-of-00030.safetensors",
937
+ "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
938
+ "model.layers.73.self_attn.o_proj.bias": "model-00027-of-00030.safetensors",
939
+ "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
940
+ "model.layers.73.self_attn.q_proj.bias": "model-00027-of-00030.safetensors",
941
+ "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
942
+ "model.layers.73.self_attn.v_proj.bias": "model-00027-of-00030.safetensors",
943
+ "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
944
+ "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
945
+ "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
946
+ "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
947
+ "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
948
+ "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
949
+ "model.layers.74.self_attn.k_proj.bias": "model-00027-of-00030.safetensors",
950
+ "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
951
+ "model.layers.74.self_attn.o_proj.bias": "model-00028-of-00030.safetensors",
952
+ "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
953
+ "model.layers.74.self_attn.q_proj.bias": "model-00027-of-00030.safetensors",
954
+ "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
955
+ "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00030.safetensors",
956
+ "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
957
+ "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
958
+ "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
959
+ "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
960
+ "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
961
+ "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
962
+ "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00030.safetensors",
963
+ "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
964
+ "model.layers.75.self_attn.o_proj.bias": "model-00028-of-00030.safetensors",
965
+ "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
966
+ "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00030.safetensors",
967
+ "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
968
+ "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00030.safetensors",
969
+ "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
970
+ "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors",
971
+ "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
972
+ "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
973
+ "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
974
+ "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
975
+ "model.layers.76.self_attn.k_proj.bias": "model-00028-of-00030.safetensors",
976
+ "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
977
+ "model.layers.76.self_attn.o_proj.bias": "model-00028-of-00030.safetensors",
978
+ "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
979
+ "model.layers.76.self_attn.q_proj.bias": "model-00028-of-00030.safetensors",
980
+ "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
981
+ "model.layers.76.self_attn.v_proj.bias": "model-00028-of-00030.safetensors",
982
+ "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
983
+ "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
984
+ "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
985
+ "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
986
+ "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
987
+ "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
988
+ "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00030.safetensors",
989
+ "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
990
+ "model.layers.77.self_attn.o_proj.bias": "model-00029-of-00030.safetensors",
991
+ "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
992
+ "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00030.safetensors",
993
+ "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
994
+ "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00030.safetensors",
995
+ "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
996
+ "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
997
+ "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
998
+ "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
999
+ "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
1000
+ "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
1001
+ "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00030.safetensors",
1002
+ "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
1003
+ "model.layers.78.self_attn.o_proj.bias": "model-00029-of-00030.safetensors",
1004
+ "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
1005
+ "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00030.safetensors",
1006
+ "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
1007
+ "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00030.safetensors",
1008
+ "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
1009
+ "model.layers.79.input_layernorm.weight": "model-00030-of-00030.safetensors",
1010
+ "model.layers.79.mlp.down_proj.weight": "model-00030-of-00030.safetensors",
1011
+ "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
1012
+ "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
1013
+ "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
1014
+ "model.layers.79.self_attn.k_proj.bias": "model-00029-of-00030.safetensors",
1015
+ "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
1016
+ "model.layers.79.self_attn.o_proj.bias": "model-00029-of-00030.safetensors",
1017
+ "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
1018
+ "model.layers.79.self_attn.q_proj.bias": "model-00029-of-00030.safetensors",
1019
+ "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
1020
+ "model.layers.79.self_attn.v_proj.bias": "model-00029-of-00030.safetensors",
1021
+ "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
1022
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
1023
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
1024
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
1025
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
1026
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
1027
+ "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00030.safetensors",
1028
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
1029
+ "model.layers.8.self_attn.o_proj.bias": "model-00004-of-00030.safetensors",
1030
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
1031
+ "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00030.safetensors",
1032
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
1033
+ "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00030.safetensors",
1034
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
1035
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00030.safetensors",
1036
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
1037
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
1038
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
1039
+ "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
1040
+ "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00030.safetensors",
1041
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
1042
+ "model.layers.9.self_attn.o_proj.bias": "model-00004-of-00030.safetensors",
1043
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
1044
+ "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00030.safetensors",
1045
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
1046
+ "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00030.safetensors",
1047
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
1048
+ "model.norm.weight": "model-00030-of-00030.safetensors"
1049
+ }
1050
+ }
output-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27dbc69f3380babc84c8fdadfd425edd28726f39f62cd7baf75350d0af9f711c
3
+ size 8589761092
output-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ff651f8c2dddfcc70695d087c3d8c1d2ff3189b527aa0be9266063b4db09a8
3
+ size 8568821628
output-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafb11fcb1536c6c4f1bbdc271b74a9eb93fa7acc12feee968e94f0305d30f2b
3
+ size 8560527464
output-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35536df30d76b0ecc9b17d92a6d8145b1c2330827fc4dc5b2aa7032568ac4ce
3
+ size 8589435368
output-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45619f8a21eab27c408ad89f817d5671a9abbbf694b76b996e027c6319fc5298
3
+ size 4068602960
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,1677 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|extra_0|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|extra_1|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|extra_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|extra_3|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|extra_4|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|extra_5|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|extra_6|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|extra_7|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|extra_8|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|extra_9|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|extra_10|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<|extra_11|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "151658": {
125
+ "content": "<|extra_12|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "151659": {
133
+ "content": "<|extra_13|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "151660": {
141
+ "content": "<|extra_14|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "151661": {
149
+ "content": "<|extra_15|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "151662": {
157
+ "content": "<|extra_16|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "151663": {
165
+ "content": "<|extra_17|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "151664": {
173
+ "content": "<|extra_18|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "151665": {
181
+ "content": "<|extra_19|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "151666": {
189
+ "content": "<|extra_20|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "151667": {
197
+ "content": "<|extra_21|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "151668": {
205
+ "content": "<|extra_22|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "151669": {
213
+ "content": "<|extra_23|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "151670": {
221
+ "content": "<|extra_24|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "151671": {
229
+ "content": "<|extra_25|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "151672": {
237
+ "content": "<|extra_26|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "151673": {
245
+ "content": "<|extra_27|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "151674": {
253
+ "content": "<|extra_28|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "151675": {
261
+ "content": "<|extra_29|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "151676": {
269
+ "content": "<|extra_30|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "151677": {
277
+ "content": "<|extra_31|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "151678": {
285
+ "content": "<|extra_32|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "151679": {
293
+ "content": "<|extra_33|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "151680": {
301
+ "content": "<|extra_34|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "151681": {
309
+ "content": "<|extra_35|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "151682": {
317
+ "content": "<|extra_36|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "151683": {
325
+ "content": "<|extra_37|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "151684": {
333
+ "content": "<|extra_38|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "151685": {
341
+ "content": "<|extra_39|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "151686": {
349
+ "content": "<|extra_40|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "151687": {
357
+ "content": "<|extra_41|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "151688": {
365
+ "content": "<|extra_42|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "151689": {
373
+ "content": "<|extra_43|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "151690": {
381
+ "content": "<|extra_44|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "151691": {
389
+ "content": "<|extra_45|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "151692": {
397
+ "content": "<|extra_46|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "151693": {
405
+ "content": "<|extra_47|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "151694": {
413
+ "content": "<|extra_48|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "151695": {
421
+ "content": "<|extra_49|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "151696": {
429
+ "content": "<|extra_50|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "151697": {
437
+ "content": "<|extra_51|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "151698": {
445
+ "content": "<|extra_52|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "151699": {
453
+ "content": "<|extra_53|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "151700": {
461
+ "content": "<|extra_54|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "151701": {
469
+ "content": "<|extra_55|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "151702": {
477
+ "content": "<|extra_56|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "151703": {
485
+ "content": "<|extra_57|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "151704": {
493
+ "content": "<|extra_58|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "151705": {
501
+ "content": "<|extra_59|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "151706": {
509
+ "content": "<|extra_60|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "151707": {
517
+ "content": "<|extra_61|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "151708": {
525
+ "content": "<|extra_62|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "151709": {
533
+ "content": "<|extra_63|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "151710": {
541
+ "content": "<|extra_64|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "151711": {
549
+ "content": "<|extra_65|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "151712": {
557
+ "content": "<|extra_66|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "151713": {
565
+ "content": "<|extra_67|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "151714": {
573
+ "content": "<|extra_68|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "151715": {
581
+ "content": "<|extra_69|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "151716": {
589
+ "content": "<|extra_70|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "151717": {
597
+ "content": "<|extra_71|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "151718": {
605
+ "content": "<|extra_72|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "151719": {
613
+ "content": "<|extra_73|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "151720": {
621
+ "content": "<|extra_74|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "151721": {
629
+ "content": "<|extra_75|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "151722": {
637
+ "content": "<|extra_76|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "151723": {
645
+ "content": "<|extra_77|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "151724": {
653
+ "content": "<|extra_78|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "151725": {
661
+ "content": "<|extra_79|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "151726": {
669
+ "content": "<|extra_80|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "151727": {
677
+ "content": "<|extra_81|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "151728": {
685
+ "content": "<|extra_82|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "151729": {
693
+ "content": "<|extra_83|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "151730": {
701
+ "content": "<|extra_84|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "151731": {
709
+ "content": "<|extra_85|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "151732": {
717
+ "content": "<|extra_86|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "151733": {
725
+ "content": "<|extra_87|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "151734": {
733
+ "content": "<|extra_88|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "151735": {
741
+ "content": "<|extra_89|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "151736": {
749
+ "content": "<|extra_90|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "151737": {
757
+ "content": "<|extra_91|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "151738": {
765
+ "content": "<|extra_92|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "151739": {
773
+ "content": "<|extra_93|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "151740": {
781
+ "content": "<|extra_94|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "151741": {
789
+ "content": "<|extra_95|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "151742": {
797
+ "content": "<|extra_96|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "151743": {
805
+ "content": "<|extra_97|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "151744": {
813
+ "content": "<|extra_98|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "151745": {
821
+ "content": "<|extra_99|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "151746": {
829
+ "content": "<|extra_100|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "151747": {
837
+ "content": "<|extra_101|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "151748": {
845
+ "content": "<|extra_102|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "151749": {
853
+ "content": "<|extra_103|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "151750": {
861
+ "content": "<|extra_104|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "151751": {
869
+ "content": "<|extra_105|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "151752": {
877
+ "content": "<|extra_106|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "151753": {
885
+ "content": "<|extra_107|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "151754": {
893
+ "content": "<|extra_108|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "151755": {
901
+ "content": "<|extra_109|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "151756": {
909
+ "content": "<|extra_110|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "151757": {
917
+ "content": "<|extra_111|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "151758": {
925
+ "content": "<|extra_112|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "151759": {
933
+ "content": "<|extra_113|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "151760": {
941
+ "content": "<|extra_114|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "151761": {
949
+ "content": "<|extra_115|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "151762": {
957
+ "content": "<|extra_116|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "151763": {
965
+ "content": "<|extra_117|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "151764": {
973
+ "content": "<|extra_118|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "151765": {
981
+ "content": "<|extra_119|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "151766": {
989
+ "content": "<|extra_120|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "151767": {
997
+ "content": "<|extra_121|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "151768": {
1005
+ "content": "<|extra_122|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "151769": {
1013
+ "content": "<|extra_123|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "151770": {
1021
+ "content": "<|extra_124|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "151771": {
1029
+ "content": "<|extra_125|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "151772": {
1037
+ "content": "<|extra_126|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "151773": {
1045
+ "content": "<|extra_127|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "151774": {
1053
+ "content": "<|extra_128|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "151775": {
1061
+ "content": "<|extra_129|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "151776": {
1069
+ "content": "<|extra_130|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "151777": {
1077
+ "content": "<|extra_131|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "151778": {
1085
+ "content": "<|extra_132|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "151779": {
1093
+ "content": "<|extra_133|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "151780": {
1101
+ "content": "<|extra_134|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "151781": {
1109
+ "content": "<|extra_135|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "151782": {
1117
+ "content": "<|extra_136|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "151783": {
1125
+ "content": "<|extra_137|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "151784": {
1133
+ "content": "<|extra_138|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "151785": {
1141
+ "content": "<|extra_139|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "151786": {
1149
+ "content": "<|extra_140|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "151787": {
1157
+ "content": "<|extra_141|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "151788": {
1165
+ "content": "<|extra_142|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "151789": {
1173
+ "content": "<|extra_143|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "151790": {
1181
+ "content": "<|extra_144|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "151791": {
1189
+ "content": "<|extra_145|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "151792": {
1197
+ "content": "<|extra_146|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "151793": {
1205
+ "content": "<|extra_147|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "151794": {
1213
+ "content": "<|extra_148|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "151795": {
1221
+ "content": "<|extra_149|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "151796": {
1229
+ "content": "<|extra_150|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "151797": {
1237
+ "content": "<|extra_151|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "151798": {
1245
+ "content": "<|extra_152|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "151799": {
1253
+ "content": "<|extra_153|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "151800": {
1261
+ "content": "<|extra_154|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "151801": {
1269
+ "content": "<|extra_155|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "151802": {
1277
+ "content": "<|extra_156|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "151803": {
1285
+ "content": "<|extra_157|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "151804": {
1293
+ "content": "<|extra_158|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "151805": {
1301
+ "content": "<|extra_159|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "151806": {
1309
+ "content": "<|extra_160|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "151807": {
1317
+ "content": "<|extra_161|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "151808": {
1325
+ "content": "<|extra_162|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "151809": {
1333
+ "content": "<|extra_163|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "151810": {
1341
+ "content": "<|extra_164|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "151811": {
1349
+ "content": "<|extra_165|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "151812": {
1357
+ "content": "<|extra_166|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "151813": {
1365
+ "content": "<|extra_167|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "151814": {
1373
+ "content": "<|extra_168|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "151815": {
1381
+ "content": "<|extra_169|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "151816": {
1389
+ "content": "<|extra_170|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "151817": {
1397
+ "content": "<|extra_171|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "151818": {
1405
+ "content": "<|extra_172|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "151819": {
1413
+ "content": "<|extra_173|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "151820": {
1421
+ "content": "<|extra_174|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "151821": {
1429
+ "content": "<|extra_175|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "151822": {
1437
+ "content": "<|extra_176|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "151823": {
1445
+ "content": "<|extra_177|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "151824": {
1453
+ "content": "<|extra_178|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "151825": {
1461
+ "content": "<|extra_179|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "151826": {
1469
+ "content": "<|extra_180|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "151827": {
1477
+ "content": "<|extra_181|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "151828": {
1485
+ "content": "<|extra_182|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "151829": {
1493
+ "content": "<|extra_183|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "151830": {
1501
+ "content": "<|extra_184|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "151831": {
1509
+ "content": "<|extra_185|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "151832": {
1517
+ "content": "<|extra_186|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "151833": {
1525
+ "content": "<|extra_187|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "151834": {
1533
+ "content": "<|extra_188|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "151835": {
1541
+ "content": "<|extra_189|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "151836": {
1549
+ "content": "<|extra_190|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "151837": {
1557
+ "content": "<|extra_191|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "151838": {
1565
+ "content": "<|extra_192|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "151839": {
1573
+ "content": "<|extra_193|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "151840": {
1581
+ "content": "<|extra_194|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "151841": {
1589
+ "content": "<|extra_195|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "151842": {
1597
+ "content": "<|extra_196|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "151843": {
1605
+ "content": "<|extra_197|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "151844": {
1613
+ "content": "<|extra_198|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "151845": {
1621
+ "content": "<|extra_199|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "151846": {
1629
+ "content": "<|extra_200|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "151847": {
1637
+ "content": "<|extra_201|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "151848": {
1645
+ "content": "<|extra_202|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "151849": {
1653
+ "content": "<|extra_203|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "151850": {
1661
+ "content": "<|extra_204|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ }
1668
+ },
1669
+ "bos_token": "<|endoftext|>",
1670
+ "clean_up_tokenization_spaces": true,
1671
+ "eos_token": "<|endoftext|>",
1672
+ "model_max_length": 4096,
1673
+ "padding_side": "left",
1674
+ "split_special_tokens": false,
1675
+ "tokenizer_class": "GPT2Tokenizer",
1676
+ "unk_token": "<|endoftext|>"
1677
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff