Hugging Face's logo

THUDM
/
glm-4-9b

Text Generation
Transformers
Safetensors
Chinese
English
chatglm
glm
thudm
custom_code
Model card Files Community
16

Converting to native Transformers

#15
by cyrilvallez HF staff - opened
base: refs/heads/main
←
from: refs/pr/15
Discussion Files changed
+546
-368
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. config.json +23 -36
  3. generation_config.json +3 -6
  4. model-00001-of-00010.safetensors → model-00001-of-00004.safetensors +2 -2
  5. model-00002-of-00010.safetensors → model-00002-of-00004.safetensors +2 -2
  6. model-00003-of-00010.safetensors → model-00003-of-00004.safetensors +2 -2
  7. model-00004-of-00010.safetensors → model-00004-of-00004.safetensors +2 -2
  8. model-00005-of-00010.safetensors +0 -3
  9. model-00006-of-00010.safetensors +0 -3
  10. model-00007-of-00010.safetensors +0 -3
  11. model-00008-of-00010.safetensors +0 -3
  12. model-00009-of-00010.safetensors +0 -3
  13. model-00010-of-00010.safetensors +0 -3
  14. model.safetensors.index.json +444 -285
  15. special_tokens_map.json +32 -0
  16. tokenizer.json +3 -0
  17. tokenizer_config.json +28 -11
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,43 +1,30 @@
1
  {
2
- "_name_or_path": "THUDM/glm-4-9b",
3
- "model_type": "chatglm",
4
  "architectures": [
5
- "ChatGLMModel"
6
  ],
7
- "auto_map": {
8
- "AutoConfig": "configuration_chatglm.ChatGLMConfig",
9
- "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
10
- "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
11
- "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
12
- "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
13
- },
14
- "add_bias_linear": false,
15
- "add_qkv_bias": true,
16
- "apply_query_key_layer_scaling": true,
17
- "apply_residual_connection_post_layernorm": false,
18
  "attention_dropout": 0.0,
19
- "attention_softmax_in_fp32": true,
20
- "attn_implementation": "sdpa",
21
- "bias_dropout_fusion": true,
22
- "ffn_hidden_size": 13696,
23
- "fp32_residual_connection": false,
24
- "hidden_dropout": 0.0,
 
25
  "hidden_size": 4096,
26
- "kv_channels": 128,
27
- "layernorm_epsilon": 0.00000015625,
28
- "multi_query_attention": true,
29
- "multi_query_group_num": 2,
30
  "num_attention_heads": 32,
31
- "num_layers": 40,
32
- "original_rope": true,
33
- "padded_vocab_size": 151552,
34
- "post_layer_norm": true,
35
- "rmsnorm": true,
36
- "seq_length": 8192,
37
- "use_cache": true,
38
- "torch_dtype": "bfloat16",
39
- "transformers_version": "4.44.0",
40
  "tie_word_embeddings": false,
41
- "eos_token_id": [151329, 151336, 151338],
42
- "pad_token_id": 151329
43
- }
 
 
 
1
  {
 
 
2
  "architectures": [
3
+ "GlmForCausalLM"
4
  ],
5
+ "attention_bias": true,
 
 
 
 
 
 
 
 
 
 
6
  "attention_dropout": 0.0,
7
+ "eos_token_id": [
8
+ 151329,
9
+ 151336,
10
+ 151338
11
+ ],
12
+ "head_dim": 128,
13
+ "hidden_act": "silu",
14
  "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 13696,
17
+ "max_position_embeddings": 8192,
18
+ "model_type": "glm",
19
  "num_attention_heads": 32,
20
+ "num_hidden_layers": 40,
21
+ "num_key_value_heads": 2,
22
+ "pad_token_id": 151329,
23
+ "rms_norm_eps": 1.5625e-07,
24
+ "rope_theta": 10000.0,
 
 
 
 
25
  "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.46.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 151552
30
+ }
generation_config.json CHANGED
@@ -1,13 +1,10 @@
1
  {
 
2
  "eos_token_id": [
3
  151329,
4
  151336,
5
  151338
6
  ],
7
  "pad_token_id": 151329,
8
- "do_sample": true,
9
- "temperature": 0.8,
10
- "max_length": 8192,
11
- "top_p": 0.8,
12
- "transformers_version": "4.44.0"
13
- }
 
1
  {
2
+ "_from_model_config": true,
3
  "eos_token_id": [
4
  151329,
5
  151336,
6
  151338
7
  ],
8
  "pad_token_id": 151329,
9
+ "transformers_version": "4.46.0.dev0"
10
+ }
 
 
 
 
model-00001-of-00010.safetensors → model-00001-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f546f3719e2b3db3243dc2efe2962b06415271b8e54bc1b32e6c01c70ee6005
3
- size 1945161760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f09ad21f16c4cc2e6662d0f77ab755163e39502441d9add215a3b7d383376c
3
+ size 4984133600
model-00002-of-00010.safetensors → model-00002-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70c890a1210e47e291b6ae99e76032c9848c5bcbd566c29e788e41ea89cf550a
3
- size 1815217640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca240fcf5bf71492118f4e12d530a93c0ad80508e08c8b110b1c6f405078f9f4
3
+ size 4895075168
model-00003-of-00010.safetensors → model-00003-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24f8f9dc017b1a03a4ef6aeec68fa857065ea036ee4e534c5040d1835ac07a66
3
- size 1968291912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf5674040c8ef05e8c95baab3eab8410c7f00339b6e2327d22f906b731afb7a
3
+ size 4895075184
model-00004-of-00010.safetensors → model-00004-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb538847b54eef09793b376342dafa17de437524a33ab99b8f0b9eeb5147dfdd
3
- size 1927406992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337e11bfa336ef43b0a19b45bca5096eb53f2b847306d9cc2d9b318030ef6819
3
+ size 4025669744
model-00005-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09464aa91cbb9bbf2cfd38c21538999e9c5fafc6a64a526621b619a6cf3122b
3
- size 1815217672
 
 
 
 
model-00006-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b8fb6a9786f4a6ac557ebcd9c7244d9e5865ef796c4d158b669bc91a63c450d
3
- size 1968291952
 
 
 
 
model-00007-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:25c66dee95a67aa4e8ae6bee424431947718920e24f1760fe364615590634634
3
- size 1927406992
 
 
 
 
model-00008-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e49c65fd473d8ec9a92882d182a05caaff852ddb52a81037b0d441528565ba4
3
- size 1815217672
 
 
 
 
model-00009-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d37f19bd367ab6243c5a77c8b1944597b5d53805598e833201d34d6ba4fca558
3
- size 1968291952
 
 
 
 
model-00010-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:71f9de8ae7a4df6c37f5d8fa8cb9209b3e8973c1bc662898f90b0b95d2338a64
3
- size 1649436712
 
 
 
 
model.safetensors.index.json CHANGED
@@ -1,291 +1,450 @@
1
  {
2
  "metadata": {
3
- "total_size": 18799902784
4
  },
5
  "weight_map": {
6
- "transformer.embedding.word_embeddings.weight": "model-00001-of-00010.safetensors",
7
- "transformer.encoder.final_layernorm.weight": "model-00010-of-00010.safetensors",
8
- "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
9
- "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00010.safetensors",
10
- "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00010.safetensors",
11
- "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
12
- "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00010.safetensors",
13
- "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00010.safetensors",
14
- "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00010.safetensors",
15
- "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
16
- "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
17
- "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00010.safetensors",
18
- "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
19
- "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00010.safetensors",
20
- "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00010.safetensors",
21
- "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00010.safetensors",
22
- "transformer.encoder.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
23
- "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
24
- "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
25
- "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
26
- "transformer.encoder.layers.10.self_attention.dense.weight": "model-00003-of-00010.safetensors",
27
- "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
28
- "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
29
- "transformer.encoder.layers.11.input_layernorm.weight": "model-00003-of-00010.safetensors",
30
- "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
31
- "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
32
- "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
33
- "transformer.encoder.layers.11.self_attention.dense.weight": "model-00004-of-00010.safetensors",
34
- "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
35
- "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
36
- "transformer.encoder.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
37
- "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
38
- "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
39
- "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
40
- "transformer.encoder.layers.12.self_attention.dense.weight": "model-00004-of-00010.safetensors",
41
- "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
42
- "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
43
- "transformer.encoder.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
44
- "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
45
- "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
46
- "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
47
- "transformer.encoder.layers.13.self_attention.dense.weight": "model-00004-of-00010.safetensors",
48
- "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
49
- "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
50
- "transformer.encoder.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
51
- "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
52
- "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
53
- "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
54
- "transformer.encoder.layers.14.self_attention.dense.weight": "model-00004-of-00010.safetensors",
55
- "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
56
- "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
57
- "transformer.encoder.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
58
- "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
59
- "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
60
- "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
61
- "transformer.encoder.layers.15.self_attention.dense.weight": "model-00004-of-00010.safetensors",
62
- "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
63
- "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
64
- "transformer.encoder.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
65
- "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
66
- "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
67
- "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
68
- "transformer.encoder.layers.16.self_attention.dense.weight": "model-00005-of-00010.safetensors",
69
- "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
70
- "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
71
- "transformer.encoder.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
72
- "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
73
- "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
74
- "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
75
- "transformer.encoder.layers.17.self_attention.dense.weight": "model-00005-of-00010.safetensors",
76
- "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
77
- "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
78
- "transformer.encoder.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
79
- "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
80
- "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
81
- "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
82
- "transformer.encoder.layers.18.self_attention.dense.weight": "model-00005-of-00010.safetensors",
83
- "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
84
- "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
85
- "transformer.encoder.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
86
- "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
87
- "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
88
- "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
89
- "transformer.encoder.layers.19.self_attention.dense.weight": "model-00005-of-00010.safetensors",
90
- "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
91
- "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
92
- "transformer.encoder.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors",
93
- "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
94
- "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
95
- "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
96
- "transformer.encoder.layers.2.self_attention.dense.weight": "model-00002-of-00010.safetensors",
97
- "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
98
- "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
99
- "transformer.encoder.layers.20.input_layernorm.weight": "model-00005-of-00010.safetensors",
100
- "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
101
- "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
102
- "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
103
- "transformer.encoder.layers.20.self_attention.dense.weight": "model-00005-of-00010.safetensors",
104
- "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
105
- "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
106
- "transformer.encoder.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
107
- "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
108
- "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
109
- "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
110
- "transformer.encoder.layers.21.self_attention.dense.weight": "model-00006-of-00010.safetensors",
111
- "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
112
- "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
113
- "transformer.encoder.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
114
- "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
115
- "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
116
- "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
117
- "transformer.encoder.layers.22.self_attention.dense.weight": "model-00006-of-00010.safetensors",
118
- "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
119
- "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
120
- "transformer.encoder.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
121
- "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
122
- "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
123
- "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
124
- "transformer.encoder.layers.23.self_attention.dense.weight": "model-00006-of-00010.safetensors",
125
- "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
126
- "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
127
- "transformer.encoder.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors",
128
- "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
129
- "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
130
- "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
131
- "transformer.encoder.layers.24.self_attention.dense.weight": "model-00006-of-00010.safetensors",
132
- "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
133
- "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
134
- "transformer.encoder.layers.25.input_layernorm.weight": "model-00006-of-00010.safetensors",
135
- "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
136
- "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
137
- "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
138
- "transformer.encoder.layers.25.self_attention.dense.weight": "model-00007-of-00010.safetensors",
139
- "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
140
- "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
141
- "transformer.encoder.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
142
- "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
143
- "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
144
- "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
145
- "transformer.encoder.layers.26.self_attention.dense.weight": "model-00007-of-00010.safetensors",
146
- "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
147
- "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
148
- "transformer.encoder.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
149
- "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
150
- "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
151
- "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
152
- "transformer.encoder.layers.27.self_attention.dense.weight": "model-00007-of-00010.safetensors",
153
- "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
154
- "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
155
- "transformer.encoder.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
156
- "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
157
- "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
158
- "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
159
- "transformer.encoder.layers.28.self_attention.dense.weight": "model-00007-of-00010.safetensors",
160
- "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
161
- "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
162
- "transformer.encoder.layers.29.input_layernorm.weight": "model-00007-of-00010.safetensors",
163
- "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
164
- "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
165
- "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
166
- "transformer.encoder.layers.29.self_attention.dense.weight": "model-00007-of-00010.safetensors",
167
- "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
168
- "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
169
- "transformer.encoder.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
170
- "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
171
- "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
172
- "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
173
- "transformer.encoder.layers.3.self_attention.dense.weight": "model-00002-of-00010.safetensors",
174
- "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
175
- "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
176
- "transformer.encoder.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
177
- "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
178
- "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
179
- "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
180
- "transformer.encoder.layers.30.self_attention.dense.weight": "model-00008-of-00010.safetensors",
181
- "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
182
- "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
183
- "transformer.encoder.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
184
- "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
185
- "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
186
- "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
187
- "transformer.encoder.layers.31.self_attention.dense.weight": "model-00008-of-00010.safetensors",
188
- "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
189
- "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
190
- "transformer.encoder.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
191
- "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
192
- "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
193
- "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
194
- "transformer.encoder.layers.32.self_attention.dense.weight": "model-00008-of-00010.safetensors",
195
- "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
196
- "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
197
- "transformer.encoder.layers.33.input_layernorm.weight": "model-00008-of-00010.safetensors",
198
- "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
199
- "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
200
- "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
201
- "transformer.encoder.layers.33.self_attention.dense.weight": "model-00008-of-00010.safetensors",
202
- "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
203
- "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
204
- "transformer.encoder.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors",
205
- "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
206
- "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
207
- "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
208
- "transformer.encoder.layers.34.self_attention.dense.weight": "model-00008-of-00010.safetensors",
209
- "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
210
- "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
211
- "transformer.encoder.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
212
- "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
213
- "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
214
- "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
215
- "transformer.encoder.layers.35.self_attention.dense.weight": "model-00009-of-00010.safetensors",
216
- "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
217
- "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
218
- "transformer.encoder.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
219
- "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
220
- "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
221
- "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
222
- "transformer.encoder.layers.36.self_attention.dense.weight": "model-00009-of-00010.safetensors",
223
- "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
224
- "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
225
- "transformer.encoder.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors",
226
- "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
227
- "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
228
- "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
229
- "transformer.encoder.layers.37.self_attention.dense.weight": "model-00009-of-00010.safetensors",
230
- "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
231
- "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
232
- "transformer.encoder.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors",
233
- "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
234
- "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
235
- "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
236
- "transformer.encoder.layers.38.self_attention.dense.weight": "model-00009-of-00010.safetensors",
237
- "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
238
- "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
239
- "transformer.encoder.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
240
- "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00010-of-00010.safetensors",
241
- "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00010-of-00010.safetensors",
242
- "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
243
- "transformer.encoder.layers.39.self_attention.dense.weight": "model-00010-of-00010.safetensors",
244
- "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00010-of-00010.safetensors",
245
- "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00010-of-00010.safetensors",
246
- "transformer.encoder.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
247
- "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
248
- "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
249
- "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
250
- "transformer.encoder.layers.4.self_attention.dense.weight": "model-00002-of-00010.safetensors",
251
- "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
252
- "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
253
- "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
254
- "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
255
- "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
256
- "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
257
- "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00010.safetensors",
258
- "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
259
- "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
260
- "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
261
- "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
262
- "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
263
- "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
264
- "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00010.safetensors",
265
- "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
266
- "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
267
- "transformer.encoder.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
268
- "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
269
- "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
270
- "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
271
- "transformer.encoder.layers.7.self_attention.dense.weight": "model-00003-of-00010.safetensors",
272
- "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
273
- "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
274
- "transformer.encoder.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
275
- "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
276
- "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
277
- "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
278
- "transformer.encoder.layers.8.self_attention.dense.weight": "model-00003-of-00010.safetensors",
279
- "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
280
- "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
281
- "transformer.encoder.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
282
- "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
283
- "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
284
- "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
285
- "transformer.encoder.layers.9.self_attention.dense.weight": "model-00003-of-00010.safetensors",
286
- "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
287
- "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
288
- "transformer.output_layer.weight": "model-00010-of-00010.safetensors",
289
- "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00010.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290
  }
291
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 18799902720
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
112
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
123
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
126
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
142
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
144
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
145
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
146
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
148
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
153
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
154
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
155
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
156
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
157
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
159
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
167
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
168
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
169
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
170
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
171
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
178
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
181
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
189
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
192
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
203
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
214
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
225
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
244
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
255
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
258
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
277
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
278
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
280
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
287
+ "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
288
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
289
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
290
+ "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
291
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
292
+ "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
296
+ "model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
297
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
298
+ "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
299
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
300
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
301
+ "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
302
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
303
+ "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
307
+ "model.layers.33.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
308
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
309
+ "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
310
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
311
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
312
+ "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
313
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
314
+ "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
318
+ "model.layers.34.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
319
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
320
+ "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
321
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
322
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
323
+ "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
324
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
325
+ "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
329
+ "model.layers.35.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
331
+ "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
332
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
333
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
334
+ "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
335
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
338
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
339
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
340
+ "model.layers.36.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
341
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
342
+ "model.layers.36.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
343
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
344
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
345
+ "model.layers.36.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
346
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
347
+ "model.layers.36.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
348
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
349
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
350
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
351
+ "model.layers.37.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
352
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
353
+ "model.layers.37.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
354
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
355
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
356
+ "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
357
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
358
+ "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
359
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
360
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
361
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
362
+ "model.layers.38.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
363
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
364
+ "model.layers.38.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
365
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
366
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
367
+ "model.layers.38.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
368
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
369
+ "model.layers.38.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
370
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
371
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
372
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
373
+ "model.layers.39.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
374
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
375
+ "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
376
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
377
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
378
+ "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
379
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
380
+ "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
381
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
382
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
383
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
384
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
385
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
386
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
387
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
388
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
389
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
390
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
391
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
392
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
393
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
394
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
395
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
396
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
397
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
398
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
399
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
400
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
401
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
402
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
403
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
405
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
406
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
407
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
408
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
409
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
410
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
411
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
412
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
413
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
414
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
415
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
416
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
417
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
418
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
419
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
420
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
421
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
422
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
423
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
424
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
425
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
426
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
427
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
428
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
429
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
430
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
431
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
432
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
433
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
434
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
435
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
436
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
437
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
438
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
439
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
440
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
441
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
442
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
443
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
444
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
445
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
446
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
447
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
448
+ "model.norm.weight": "model-00004-of-00004.safetensors"
449
  }
450
  }
special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "[MASK]",
5
+ "[gMASK]",
6
+ "[sMASK]",
7
+ "<sop>",
8
+ "<eop>",
9
+ "<|system|>",
10
+ "<|user|>",
11
+ "<|assistant|>",
12
+ "<|observation|>",
13
+ "<|begin_of_image|>",
14
+ "<|end_of_image|>",
15
+ "<|begin_of_video|>",
16
+ "<|end_of_video|>"
17
+ ],
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7269d6daa6328de533def0082ff9d3a825bb89036cbcc665c324f941f67fbf
3
+ size 19967863
tokenizer_config.json CHANGED
@@ -1,10 +1,4 @@
1
  {
2
- "auto_map": {
3
- "AutoTokenizer": [
4
- "tokenization_chatglm.ChatGLM4Tokenizer",
5
- null
6
- ]
7
- },
8
  "added_tokens_decoder": {
9
  "151329": {
10
  "content": "<|endoftext|>",
@@ -119,15 +113,38 @@
119
  "special": true
120
  }
121
  },
122
- "additional_special_tokens": ["<|endoftext|>", "[MASK]", "[gMASK]", "[sMASK]", "<sop>", "<eop>", "<|system|>",
123
- "<|user|>", "<|assistant|>", "<|observation|>", "<|begin_of_image|>", "<|end_of_image|>",
124
- "<|begin_of_video|>", "<|end_of_video|>"],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
125
  "clean_up_tokenization_spaces": false,
126
  "do_lower_case": false,
127
  "eos_token": "<|endoftext|>",
128
- "pad_token": "<|endoftext|>",
 
 
 
129
  "model_max_length": 8000,
 
130
  "padding_side": "left",
131
  "remove_space": false,
132
- "tokenizer_class": "ChatGLM4Tokenizer"
133
  }
 
1
  {
 
 
 
 
 
 
2
  "added_tokens_decoder": {
3
  "151329": {
4
  "content": "<|endoftext|>",
 
113
  "special": true
114
  }
115
  },
116
+ "additional_special_tokens": [
117
+ "<|endoftext|>",
118
+ "[MASK]",
119
+ "[gMASK]",
120
+ "[sMASK]",
121
+ "<sop>",
122
+ "<eop>",
123
+ "<|system|>",
124
+ "<|user|>",
125
+ "<|assistant|>",
126
+ "<|observation|>",
127
+ "<|begin_of_image|>",
128
+ "<|end_of_image|>",
129
+ "<|begin_of_video|>",
130
+ "<|end_of_video|>"
131
+ ],
132
+ "auto_map": {
133
+ "AutoTokenizer": [
134
+ "tokenization_chatglm.ChatGLM4Tokenizer",
135
+ null
136
+ ]
137
+ },
138
  "clean_up_tokenization_spaces": false,
139
  "do_lower_case": false,
140
  "eos_token": "<|endoftext|>",
141
+ "model_input_names": [
142
+ "input_ids",
143
+ "attention_mask"
144
+ ],
145
  "model_max_length": 8000,
146
+ "pad_token": "<|endoftext|>",
147
  "padding_side": "left",
148
  "remove_space": false,
149
+ "tokenizer_class": "PreTrainedTokenizerFast"
150
  }