sammysun0711 commited on
Commit
1a87f3c
1 Parent(s): f667769

Upgrade to AquilaChat-7B v0.6 configurations

Browse files
BAAI_Aquila_Model_License.pdf DELETED
Binary file (225 kB)
 
BAAI_Aquila_Model_License_Agreement.pdf ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "aquilachat-7b-hf",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -21,8 +20,8 @@
21
  "pad_token_id": 0,
22
  "rms_norm_eps": 1e-05,
23
  "tie_word_embeddings": false,
24
- "torch_dtype": "float32",
25
- "transformers_version": "4.30.2",
26
  "unk_token_id": 0,
27
  "use_cache": true,
28
  "vocab_size": 100008
 
1
  {
 
2
  "architectures": [
3
  "LlamaForCausalLM"
4
  ],
 
20
  "pad_token_id": 0,
21
  "rms_norm_eps": 1e-05,
22
  "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.29.2",
25
  "unk_token_id": 0,
26
  "use_cache": true,
27
  "vocab_size": 100008
convert_aquila_weights_to_hf.py CHANGED
@@ -13,16 +13,17 @@
13
  # limitations under the License.
14
  import argparse
15
  import gc
 
16
  import json
17
  import math
18
  import os
19
  import shutil
20
  import warnings
21
-
22
  import torch
 
23
 
24
  from transformers import LlamaConfig, LlamaForCausalLM, LlamaTokenizer
25
-
26
 
27
  try:
28
  from transformers import LlamaTokenizerFast
@@ -44,10 +45,10 @@ python src/transformers/models/llama/convert_llama_weights_to_hf.py \
44
  Thereafter, models can be loaded via:
45
 
46
  ```py
47
- from transformers import LlamaForCausalLM, LlamaTokenizer
48
 
49
- model = LlamaForCausalLM.from_pretrained("/output/path")
50
- tokenizer = LlamaTokenizer.from_pretrained("/output/path")
51
  ```
52
 
53
  Important note: you need to be able to host the whole model in RAM to execute this script (even if the biggest versions
@@ -93,6 +94,8 @@ def write_model(model_path, input_base_path, model_size):
93
  print("params: ", params)
94
 
95
  num_shards = NUM_SHARDS[model_size]
 
 
96
  n_layers = params["n_layers"]
97
  n_heads = params["n_heads"]
98
  n_heads_per_shard = n_heads // num_shards
@@ -100,23 +103,9 @@ def write_model(model_path, input_base_path, model_size):
100
  dims_per_head = dim // n_heads
101
  base = 10000.0
102
  inv_freq = 1.0 / (base ** (torch.arange(0, dims_per_head, 2).float() / dims_per_head))
103
-
104
- """
105
- params = {}
106
- num_shards = 1
107
- n_layers = 32
108
- n_heads = 32
109
- n_heads_per_shard = n_heads // num_shards
110
- dim = 4096
111
- dims_per_head = dim // n_heads
112
- base = 10000.0
113
- inv_freq = 1.0 / (base ** (torch.arange(0, dims_per_head, 2).float() / dims_per_head))
114
 
115
- params["n_layers"] = n_layers
116
- params["n_heads"] = n_heads
117
- params["dim"] = dim
118
- params["norm_eps"] = 1e-05
119
- """
120
 
121
  # permute for sliced rotary
122
  def permute(w):
@@ -246,6 +235,17 @@ def write_model(model_path, input_base_path, model_size):
246
  num_hidden_layers=params["n_layers"],
247
  rms_norm_eps=params["norm_eps"],
248
  )
 
 
 
 
 
 
 
 
 
 
 
249
  config.save_pretrained(tmp_model_path)
250
 
251
  # Make space so we can load the model properly now.
@@ -263,13 +263,20 @@ def write_model(model_path, input_base_path, model_size):
263
  shutil.rmtree(tmp_model_path)
264
 
265
 
266
- def write_tokenizer(tokenizer_path, input_tokenizer_path):
267
- # Initialize the tokenizer based on the `spm` model
268
- tokenizer_class = LlamaTokenizer if LlamaTokenizerFast is None else LlamaTokenizerFast
269
- print(f"Saving a {tokenizer_class.__name__} to {tokenizer_path}.")
270
- tokenizer = tokenizer_class(input_tokenizer_path)
271
- tokenizer.save_pretrained(tokenizer_path)
272
 
 
 
 
 
 
 
 
 
273
 
274
  def main():
275
  parser = argparse.ArgumentParser()
@@ -286,6 +293,7 @@ def main():
286
  help="Location to write HF model and tokenizer",
287
  )
288
  args = parser.parse_args()
 
289
  if args.model_size != "tokenizer_only":
290
  write_model(
291
  model_path=args.output_dir,
@@ -293,9 +301,9 @@ def main():
293
  input_base_path=args.input_dir,
294
  model_size=args.model_size,
295
  )
296
- #spm_path = os.path.join(args.input_dir, "tokenizer.model")
297
- #write_tokenizer(args.output_dir, spm_path)
298
-
299
 
300
  if __name__ == "__main__":
301
  main()
 
13
  # limitations under the License.
14
  import argparse
15
  import gc
16
+ import glob
17
  import json
18
  import math
19
  import os
20
  import shutil
21
  import warnings
 
22
  import torch
23
+ import urllib
24
 
25
  from transformers import LlamaConfig, LlamaForCausalLM, LlamaTokenizer
26
+ from transformers import GPTNeoXTokenizerFast
27
 
28
  try:
29
  from transformers import LlamaTokenizerFast
 
45
  Thereafter, models can be loaded via:
46
 
47
  ```py
48
+ from transformers import AutoModelForCausalLM, AutoTokenizer
49
 
50
+ model = AutoModelForCausalLM.from_pretrained("/output/path")
51
+ tokenizer = AutoTokenizer.from_pretrained("/output/path")
52
  ```
53
 
54
  Important note: you need to be able to host the whole model in RAM to execute this script (even if the biggest versions
 
94
  print("params: ", params)
95
 
96
  num_shards = NUM_SHARDS[model_size]
97
+
98
+ # Model parameters
99
  n_layers = params["n_layers"]
100
  n_heads = params["n_heads"]
101
  n_heads_per_shard = n_heads // num_shards
 
103
  dims_per_head = dim // n_heads
104
  base = 10000.0
105
  inv_freq = 1.0 / (base ** (torch.arange(0, dims_per_head, 2).float() / dims_per_head))
106
+ # Tokenizer parameters
107
+ #vocab_size = params["vocab_size"]
 
 
 
 
 
 
 
 
 
108
 
 
 
 
 
 
109
 
110
  # permute for sliced rotary
111
  def permute(w):
 
235
  num_hidden_layers=params["n_layers"],
236
  rms_norm_eps=params["norm_eps"],
237
  )
238
+ #config["_name_or_path"] = tmp_model_path
239
+ config.auto_map = {
240
+ "AutoConfig": "modeling_aquila.LlamaConfig",
241
+ "AutoModel": "modeling_aquila.LlamaModel",
242
+ "AutoModelForCausalLM": "modeling_aquila.LlamaForCausalLM"
243
+ }
244
+ config.bos_token_id = 100006
245
+ config.eos_token_id = 100007
246
+ config.pad_token_id = 0
247
+ config.unk_token_id = 0
248
+ config.vocab_size = params["vocab_size"]
249
  config.save_pretrained(tmp_model_path)
250
 
251
  # Make space so we can load the model properly now.
 
263
  shutil.rmtree(tmp_model_path)
264
 
265
 
266
+ def write_tokenizer(input_tokenizer_path, output_dir):
267
+ tokenizer_class = GPTNeoXTokenizerFast
268
+ tokenizer = tokenizer_class.from_pretrained(input_tokenizer_path)
269
+ print(f"Saving a {tokenizer_class.__name__} to {output_dir}.")
270
+ tokenizer.save_pretrained(output_dir)
 
271
 
272
+ def copy_aquila_license(input_base_path, output_dir):
273
+ for path in glob.glob(os.path.join(input_base_path, "*.pdf")):
274
+ print(f"Copy Aquila License file from {path} to {output_dir}")
275
+ shutil.copy2(path, output_dir)
276
+
277
+ def download_modeling_aquila_file(output_dir):
278
+ url = "https://gist.githubusercontent.com/sammysun0711/4f2622dba7f7ec2dff6cdd31ea21d419/raw/0fa7e79f3fa27bf9fbb8d85e9b5bb16b5e93db88/modeling_aqulia.py"
279
+ urllib.request.urlretrieve(url, os.path.join(output_dir, "modeling_aquila.py"))
280
 
281
  def main():
282
  parser = argparse.ArgumentParser()
 
293
  help="Location to write HF model and tokenizer",
294
  )
295
  args = parser.parse_args()
296
+
297
  if args.model_size != "tokenizer_only":
298
  write_model(
299
  model_path=args.output_dir,
 
301
  input_base_path=args.input_dir,
302
  model_size=args.model_size,
303
  )
304
+ copy_aquila_license(args.input_dir, args.output_dir)
305
+ write_tokenizer(args.input_dir, args.output_dir)
306
+ download_modeling_aquila_file(args.output_dir)
307
 
308
  if __name__ == "__main__":
309
  main()
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 100006,
4
  "eos_token_id": 100007,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.30.2"
7
  }
 
3
  "bos_token_id": 100006,
4
  "eos_token_id": 100007,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.29.2"
7
  }
modeling_aquila.py CHANGED
@@ -897,4 +897,4 @@ class LlamaForSequenceClassification(LlamaPreTrainedModel):
897
  past_key_values=transformer_outputs.past_key_values,
898
  hidden_states=transformer_outputs.hidden_states,
899
  attentions=transformer_outputs.attentions,
900
- )
 
897
  past_key_values=transformer_outputs.past_key_values,
898
  hidden_states=transformer_outputs.hidden_states,
899
  attentions=transformer_outputs.attentions,
900
+ )
pytorch_model.bin.index.json CHANGED
@@ -1,330 +1,330 @@
1
  {
2
  "metadata": {
3
- "total_size": 29182156800
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
- "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
- "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
- "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
- "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
- "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
- "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
- "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
- "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
- "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
- "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
- "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
- "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
- "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
- "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
- "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
- "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
- "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
- "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
- "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
- "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
- "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
- "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
29
- "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
30
- "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
31
- "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
32
- "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
33
- "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
- "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
35
- "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
- "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
37
- "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
- "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
39
- "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
40
- "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
41
- "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
42
- "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
43
- "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
44
- "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
45
- "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
46
- "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
47
- "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
48
- "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
- "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
50
- "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
51
- "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
52
- "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
53
- "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
54
- "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
55
- "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
56
- "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
57
- "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
58
- "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
59
- "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
60
- "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
61
- "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
62
- "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
- "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
64
- "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
65
- "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
66
- "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
67
- "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
68
- "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
- "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
70
- "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
71
- "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
72
- "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
73
- "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
74
- "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
75
- "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
76
- "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
- "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
78
- "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
- "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
- "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
- "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
- "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
- "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
84
- "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
- "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
86
- "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
- "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
- "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
- "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
- "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
- "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
- "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
- "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
- "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
- "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
- "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
- "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
- "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
- "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
- "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
- "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
- "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
- "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
- "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
- "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
- "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
- "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
- "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
- "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
- "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
- "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
- "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
- "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
- "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
- "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
- "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
- "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
- "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
- "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
- "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
- "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
- "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
- "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
- "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
- "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
- "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
- "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
- "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
- "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
- "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
- "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
- "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
- "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
- "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
- "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
- "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
- "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
- "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
- "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
- "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
- "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
- "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
- "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
- "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
- "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
- "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
- "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
- "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
- "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
- "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
- "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
- "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
- "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
- "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
- "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
- "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
- "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
- "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
159
- "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
160
- "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
- "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
162
- "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
163
- "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
- "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
- "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
- "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
- "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
- "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
169
- "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
170
- "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
171
- "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
172
- "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
173
- "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
174
- "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
175
- "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
176
- "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
177
- "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
178
- "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
179
- "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
180
- "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
181
- "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
182
- "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
183
- "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
184
- "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
185
- "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
186
- "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
187
- "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
- "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
- "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
- "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
- "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
- "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
- "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
- "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
- "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
- "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
197
- "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
198
- "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
199
- "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
200
- "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
201
- "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
202
- "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
203
- "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
204
- "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
205
- "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
206
- "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
207
- "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
208
- "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
209
- "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
210
- "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
211
- "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
212
- "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
213
- "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
- "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
215
- "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
216
- "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
217
- "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
- "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
219
- "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
220
- "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
221
- "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
222
- "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
223
- "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
224
- "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
225
- "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
226
- "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
227
- "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
228
- "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
- "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
230
- "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
231
- "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
232
- "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
233
- "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
234
- "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
235
- "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
236
- "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
237
- "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
238
- "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
- "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
- "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
- "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
- "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
- "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
- "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
- "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
- "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
- "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
- "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
- "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
- "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
251
- "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
252
- "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
- "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
254
- "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
255
- "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
256
- "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
257
- "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
258
- "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
- "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
- "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
- "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
- "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
- "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
- "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
- "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
- "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
- "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
- "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
269
- "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
270
- "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
271
- "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
272
- "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
273
- "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
- "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
275
- "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
276
- "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
277
- "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
- "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
- "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
- "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
- "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
- "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
- "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
- "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
- "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
- "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
287
- "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
288
- "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
- "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
290
- "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
291
- "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
292
- "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
293
- "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
294
- "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
295
- "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
296
- "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
297
- "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
298
- "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
299
- "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
300
- "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
301
- "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
302
- "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
303
- "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
304
- "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
305
- "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
306
- "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
307
- "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
308
- "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
309
- "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
310
- "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
311
- "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
312
- "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
- "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
314
- "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
315
- "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
316
- "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
317
- "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
318
- "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
- "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
320
- "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
321
- "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
322
- "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
323
- "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
324
- "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
325
- "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
326
- "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
327
- "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
328
- "model.norm.weight": "pytorch_model-00003-of-00003.bin"
329
  }
330
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 14591082496
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
329
  }
330
  }
tokenizer.json CHANGED
@@ -199806,4 +199806,4 @@
199806
  "çŃī 课ç¨ĭ"
199807
  ]
199808
  }
199809
- }
 
199806
  "çŃī 课ç¨ĭ"
199807
  ]
199808
  }
199809
+ }