Hugging Face's logo

boboliu
/
glm-4-9b-chat-FP8

Text Generation
Transformers
Safetensors
Chinese
chatglm
feature-extraction
conversational
custom_code
fp8
Model card Files Community
boboliu commited on
Commit
212faa3
•
1 Parent(s): 8d6d5ae

init

Browse files
Files changed (11) hide show
  1. README.md +13 -0
  2. added_tokens.json +16 -0
  3. config.json +57 -0
  4. generation_config.json +13 -0
  5. model-00001-of-00003.safetensors +3 -0
  6. model-00002-of-00003.safetensors +3 -0
  7. model-00003-of-00003.safetensors +3 -0
  8. model.safetensors.index.json +611 -0
  9. special_tokens_map.json +32 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +147 -0
README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: glm-4
4
+ license_link: https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE
5
+ language:
6
+ - zh
7
+ pipeline_tag: text-generation
8
+ ---
9
+ # GLM-4-9b-chat Quantized with AutoFP8
10
+
11
+ 使用 [m-a-p/COIG-CQIA](https://huggingface.co/datasets/m-a-p/COIG-CQIA) 的 COIG_pc 集作为校准量化的 [glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat) 模型。
12
+
13
+ 为 vLLM 准备。
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<eop>": 151334,
3
+ "<sop>": 151333,
4
+ "<|assistant|>": 151337,
5
+ "<|begin_of_image|>": 151339,
6
+ "<|begin_of_video|>": 151341,
7
+ "<|end_of_image|>": 151340,
8
+ "<|end_of_video|>": 151342,
9
+ "<|endoftext|>": 151329,
10
+ "<|observation|>": 151338,
11
+ "<|system|>": 151335,
12
+ "<|user|>": 151336,
13
+ "[MASK]": 151330,
14
+ "[gMASK]": 151331,
15
+ "[sMASK]": 151332
16
+ }
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "THUDM/glm-4-9b-chat",
3
+ "add_bias_linear": false,
4
+ "add_qkv_bias": true,
5
+ "apply_query_key_layer_scaling": true,
6
+ "apply_residual_connection_post_layernorm": false,
7
+ "architectures": [
8
+ "ChatGLMForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "attention_softmax_in_fp32": true,
12
+ "auto_map": {
13
+ "AutoConfig": "THUDM/glm-4-9b-chat--configuration_chatglm.ChatGLMConfig",
14
+ "AutoModel": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
15
+ "AutoModelForCausalLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
16
+ "AutoModelForSeq2SeqLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
17
+ "AutoModelForSequenceClassification": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForSequenceClassification"
18
+ },
19
+ "bias_dropout_fusion": true,
20
+ "classifier_dropout": null,
21
+ "eos_token_id": [
22
+ 151329,
23
+ 151336,
24
+ 151338
25
+ ],
26
+ "ffn_hidden_size": 13696,
27
+ "fp32_residual_connection": false,
28
+ "hidden_dropout": 0.0,
29
+ "hidden_size": 4096,
30
+ "kv_channels": 128,
31
+ "layernorm_epsilon": 1.5625e-07,
32
+ "model_type": "chatglm",
33
+ "multi_query_attention": true,
34
+ "multi_query_group_num": 2,
35
+ "num_attention_heads": 32,
36
+ "num_hidden_layers": 40,
37
+ "num_layers": 40,
38
+ "original_rope": true,
39
+ "pad_token_id": 151329,
40
+ "padded_vocab_size": 151552,
41
+ "post_layer_norm": true,
42
+ "quantization_config": {
43
+ "activation_scheme": "static",
44
+ "ignored_layers": [
45
+ "transformer.output_layer"
46
+ ],
47
+ "quant_method": "fp8"
48
+ },
49
+ "rmsnorm": true,
50
+ "rope_ratio": 500,
51
+ "seq_length": 131072,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.43.3",
55
+ "use_cache": true,
56
+ "vocab_size": 151552
57
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151329,
5
+ 151336,
6
+ 151338
7
+ ],
8
+ "max_length": 128000,
9
+ "pad_token_id": 151329,
10
+ "temperature": 0.8,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.43.3"
13
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037693ec06452184b5c37bfb2269e31db1807f1ad57041749c55fff6bda23578
3
+ size 4948752824
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c3049010af19cc50e83c8728e5a31eccb7d43c5487a548ac7ea63e4e61a503
3
+ size 4451791968
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ac1878a23796a69dbc48efd0cd45a1fc8f2b80c23b761ada772e6046578cf1
3
+ size 1241514128
model.safetensors.index.json ADDED
@@ -0,0 +1,611 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10641982784
4
+ },
5
+ "weight_map": {
6
+ "transformer.embedding.word_embeddings.weight": "model-00001-of-00003.safetensors",
7
+ "transformer.encoder.final_layernorm.weight": "model-00002-of-00003.safetensors",
8
+ "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "transformer.encoder.layers.0.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
10
+ "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
11
+ "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
12
+ "transformer.encoder.layers.0.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
13
+ "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
14
+ "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
15
+ "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.encoder.layers.0.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
17
+ "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.encoder.layers.0.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
19
+ "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
20
+ "transformer.encoder.layers.0.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
21
+ "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.encoder.layers.0.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
23
+ "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.encoder.layers.1.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
25
+ "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
27
+ "transformer.encoder.layers.1.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
28
+ "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
29
+ "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
30
+ "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "transformer.encoder.layers.1.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
32
+ "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
33
+ "transformer.encoder.layers.1.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
34
+ "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
35
+ "transformer.encoder.layers.1.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
36
+ "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
37
+ "transformer.encoder.layers.1.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
38
+ "transformer.encoder.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
39
+ "transformer.encoder.layers.10.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
40
+ "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
41
+ "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
42
+ "transformer.encoder.layers.10.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
43
+ "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
44
+ "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
45
+ "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
46
+ "transformer.encoder.layers.10.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
47
+ "transformer.encoder.layers.10.self_attention.dense.weight": "model-00001-of-00003.safetensors",
48
+ "transformer.encoder.layers.10.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
49
+ "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
50
+ "transformer.encoder.layers.10.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
51
+ "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
52
+ "transformer.encoder.layers.10.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
53
+ "transformer.encoder.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
54
+ "transformer.encoder.layers.11.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
55
+ "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
56
+ "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
57
+ "transformer.encoder.layers.11.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
58
+ "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
59
+ "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
60
+ "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
61
+ "transformer.encoder.layers.11.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
62
+ "transformer.encoder.layers.11.self_attention.dense.weight": "model-00001-of-00003.safetensors",
63
+ "transformer.encoder.layers.11.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
64
+ "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
65
+ "transformer.encoder.layers.11.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
66
+ "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
67
+ "transformer.encoder.layers.11.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
68
+ "transformer.encoder.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
69
+ "transformer.encoder.layers.12.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
70
+ "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
71
+ "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
72
+ "transformer.encoder.layers.12.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
73
+ "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
74
+ "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
75
+ "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
76
+ "transformer.encoder.layers.12.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
77
+ "transformer.encoder.layers.12.self_attention.dense.weight": "model-00001-of-00003.safetensors",
78
+ "transformer.encoder.layers.12.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
79
+ "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
80
+ "transformer.encoder.layers.12.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
81
+ "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
82
+ "transformer.encoder.layers.12.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
83
+ "transformer.encoder.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
84
+ "transformer.encoder.layers.13.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
85
+ "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
86
+ "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
87
+ "transformer.encoder.layers.13.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
88
+ "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
89
+ "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
90
+ "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
91
+ "transformer.encoder.layers.13.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
92
+ "transformer.encoder.layers.13.self_attention.dense.weight": "model-00001-of-00003.safetensors",
93
+ "transformer.encoder.layers.13.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
94
+ "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
95
+ "transformer.encoder.layers.13.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
96
+ "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
97
+ "transformer.encoder.layers.13.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
98
+ "transformer.encoder.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
99
+ "transformer.encoder.layers.14.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
100
+ "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
101
+ "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
102
+ "transformer.encoder.layers.14.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
103
+ "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
104
+ "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
105
+ "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
106
+ "transformer.encoder.layers.14.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
107
+ "transformer.encoder.layers.14.self_attention.dense.weight": "model-00001-of-00003.safetensors",
108
+ "transformer.encoder.layers.14.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
109
+ "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
110
+ "transformer.encoder.layers.14.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
111
+ "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
112
+ "transformer.encoder.layers.14.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
113
+ "transformer.encoder.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
114
+ "transformer.encoder.layers.15.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
115
+ "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
116
+ "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
117
+ "transformer.encoder.layers.15.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
118
+ "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
119
+ "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
120
+ "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "transformer.encoder.layers.15.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
122
+ "transformer.encoder.layers.15.self_attention.dense.weight": "model-00001-of-00003.safetensors",
123
+ "transformer.encoder.layers.15.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
124
+ "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
125
+ "transformer.encoder.layers.15.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
126
+ "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
127
+ "transformer.encoder.layers.15.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
128
+ "transformer.encoder.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
129
+ "transformer.encoder.layers.16.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
130
+ "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
131
+ "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
132
+ "transformer.encoder.layers.16.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
133
+ "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
134
+ "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
135
+ "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
136
+ "transformer.encoder.layers.16.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
137
+ "transformer.encoder.layers.16.self_attention.dense.weight": "model-00001-of-00003.safetensors",
138
+ "transformer.encoder.layers.16.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
139
+ "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
140
+ "transformer.encoder.layers.16.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
141
+ "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
142
+ "transformer.encoder.layers.16.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
143
+ "transformer.encoder.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
144
+ "transformer.encoder.layers.17.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
145
+ "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
146
+ "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
147
+ "transformer.encoder.layers.17.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
148
+ "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
149
+ "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
150
+ "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
151
+ "transformer.encoder.layers.17.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
152
+ "transformer.encoder.layers.17.self_attention.dense.weight": "model-00001-of-00003.safetensors",
153
+ "transformer.encoder.layers.17.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
154
+ "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
155
+ "transformer.encoder.layers.17.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
156
+ "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
157
+ "transformer.encoder.layers.17.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
158
+ "transformer.encoder.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
159
+ "transformer.encoder.layers.18.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
160
+ "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
161
+ "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
162
+ "transformer.encoder.layers.18.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
163
+ "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
164
+ "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
165
+ "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
166
+ "transformer.encoder.layers.18.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
167
+ "transformer.encoder.layers.18.self_attention.dense.weight": "model-00001-of-00003.safetensors",
168
+ "transformer.encoder.layers.18.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
169
+ "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
170
+ "transformer.encoder.layers.18.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
171
+ "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
172
+ "transformer.encoder.layers.18.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
173
+ "transformer.encoder.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
174
+ "transformer.encoder.layers.19.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
175
+ "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
176
+ "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
177
+ "transformer.encoder.layers.19.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
178
+ "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
179
+ "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
180
+ "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
181
+ "transformer.encoder.layers.19.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
182
+ "transformer.encoder.layers.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
183
+ "transformer.encoder.layers.19.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
184
+ "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
185
+ "transformer.encoder.layers.19.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
186
+ "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
187
+ "transformer.encoder.layers.19.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
188
+ "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
189
+ "transformer.encoder.layers.2.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
190
+ "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
191
+ "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
192
+ "transformer.encoder.layers.2.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
193
+ "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
194
+ "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
195
+ "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
196
+ "transformer.encoder.layers.2.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
197
+ "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
198
+ "transformer.encoder.layers.2.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
199
+ "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
200
+ "transformer.encoder.layers.2.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
201
+ "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
202
+ "transformer.encoder.layers.2.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
203
+ "transformer.encoder.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
204
+ "transformer.encoder.layers.20.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
205
+ "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
206
+ "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
207
+ "transformer.encoder.layers.20.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
208
+ "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
209
+ "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
210
+ "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
211
+ "transformer.encoder.layers.20.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
212
+ "transformer.encoder.layers.20.self_attention.dense.weight": "model-00002-of-00003.safetensors",
213
+ "transformer.encoder.layers.20.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
214
+ "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
215
+ "transformer.encoder.layers.20.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
216
+ "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
217
+ "transformer.encoder.layers.20.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
218
+ "transformer.encoder.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
219
+ "transformer.encoder.layers.21.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
220
+ "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
221
+ "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
222
+ "transformer.encoder.layers.21.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
223
+ "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
224
+ "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
225
+ "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
226
+ "transformer.encoder.layers.21.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
227
+ "transformer.encoder.layers.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
228
+ "transformer.encoder.layers.21.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
229
+ "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
230
+ "transformer.encoder.layers.21.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
231
+ "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
232
+ "transformer.encoder.layers.21.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
233
+ "transformer.encoder.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
234
+ "transformer.encoder.layers.22.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
235
+ "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
236
+ "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
237
+ "transformer.encoder.layers.22.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
238
+ "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
239
+ "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
240
+ "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
241
+ "transformer.encoder.layers.22.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
242
+ "transformer.encoder.layers.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
243
+ "transformer.encoder.layers.22.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
244
+ "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
245
+ "transformer.encoder.layers.22.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
246
+ "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
247
+ "transformer.encoder.layers.22.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
248
+ "transformer.encoder.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
249
+ "transformer.encoder.layers.23.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
250
+ "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
251
+ "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
252
+ "transformer.encoder.layers.23.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
253
+ "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
254
+ "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
255
+ "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
256
+ "transformer.encoder.layers.23.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
257
+ "transformer.encoder.layers.23.self_attention.dense.weight": "model-00002-of-00003.safetensors",
258
+ "transformer.encoder.layers.23.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
259
+ "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
260
+ "transformer.encoder.layers.23.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
261
+ "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
262
+ "transformer.encoder.layers.23.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
263
+ "transformer.encoder.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
264
+ "transformer.encoder.layers.24.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
265
+ "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
266
+ "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
267
+ "transformer.encoder.layers.24.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
268
+ "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
269
+ "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
270
+ "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
271
+ "transformer.encoder.layers.24.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
272
+ "transformer.encoder.layers.24.self_attention.dense.weight": "model-00002-of-00003.safetensors",
273
+ "transformer.encoder.layers.24.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
274
+ "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
275
+ "transformer.encoder.layers.24.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
276
+ "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
277
+ "transformer.encoder.layers.24.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
278
+ "transformer.encoder.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
279
+ "transformer.encoder.layers.25.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
280
+ "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
281
+ "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
282
+ "transformer.encoder.layers.25.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
283
+ "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
284
+ "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
285
+ "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
286
+ "transformer.encoder.layers.25.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
287
+ "transformer.encoder.layers.25.self_attention.dense.weight": "model-00002-of-00003.safetensors",
288
+ "transformer.encoder.layers.25.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
289
+ "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
290
+ "transformer.encoder.layers.25.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
291
+ "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
292
+ "transformer.encoder.layers.25.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
293
+ "transformer.encoder.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
294
+ "transformer.encoder.layers.26.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
295
+ "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
296
+ "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
297
+ "transformer.encoder.layers.26.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
298
+ "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
299
+ "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
300
+ "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
301
+ "transformer.encoder.layers.26.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
302
+ "transformer.encoder.layers.26.self_attention.dense.weight": "model-00002-of-00003.safetensors",
303
+ "transformer.encoder.layers.26.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
304
+ "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
305
+ "transformer.encoder.layers.26.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
306
+ "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
307
+ "transformer.encoder.layers.26.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
308
+ "transformer.encoder.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
309
+ "transformer.encoder.layers.27.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
310
+ "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
311
+ "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
312
+ "transformer.encoder.layers.27.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
313
+ "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
314
+ "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
315
+ "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
316
+ "transformer.encoder.layers.27.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
317
+ "transformer.encoder.layers.27.self_attention.dense.weight": "model-00002-of-00003.safetensors",
318
+ "transformer.encoder.layers.27.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
319
+ "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
320
+ "transformer.encoder.layers.27.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
321
+ "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
322
+ "transformer.encoder.layers.27.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
323
+ "transformer.encoder.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
324
+ "transformer.encoder.layers.28.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
325
+ "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
326
+ "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
327
+ "transformer.encoder.layers.28.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
328
+ "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
329
+ "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
330
+ "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
331
+ "transformer.encoder.layers.28.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
332
+ "transformer.encoder.layers.28.self_attention.dense.weight": "model-00002-of-00003.safetensors",
333
+ "transformer.encoder.layers.28.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
334
+ "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
335
+ "transformer.encoder.layers.28.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
336
+ "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
337
+ "transformer.encoder.layers.28.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
338
+ "transformer.encoder.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
339
+ "transformer.encoder.layers.29.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
340
+ "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
341
+ "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
342
+ "transformer.encoder.layers.29.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
343
+ "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
344
+ "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
345
+ "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
346
+ "transformer.encoder.layers.29.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
347
+ "transformer.encoder.layers.29.self_attention.dense.weight": "model-00002-of-00003.safetensors",
348
+ "transformer.encoder.layers.29.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
349
+ "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
350
+ "transformer.encoder.layers.29.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
351
+ "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
352
+ "transformer.encoder.layers.29.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
353
+ "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
354
+ "transformer.encoder.layers.3.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
355
+ "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
356
+ "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
357
+ "transformer.encoder.layers.3.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
358
+ "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
359
+ "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
360
+ "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
361
+ "transformer.encoder.layers.3.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
362
+ "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
363
+ "transformer.encoder.layers.3.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
364
+ "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
365
+ "transformer.encoder.layers.3.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
366
+ "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
367
+ "transformer.encoder.layers.3.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
368
+ "transformer.encoder.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
369
+ "transformer.encoder.layers.30.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
370
+ "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
371
+ "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
372
+ "transformer.encoder.layers.30.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
373
+ "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
374
+ "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
375
+ "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
376
+ "transformer.encoder.layers.30.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
377
+ "transformer.encoder.layers.30.self_attention.dense.weight": "model-00002-of-00003.safetensors",
378
+ "transformer.encoder.layers.30.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
379
+ "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
380
+ "transformer.encoder.layers.30.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
381
+ "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
382
+ "transformer.encoder.layers.30.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
383
+ "transformer.encoder.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
384
+ "transformer.encoder.layers.31.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
385
+ "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
386
+ "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
387
+ "transformer.encoder.layers.31.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
388
+ "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
389
+ "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
390
+ "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
391
+ "transformer.encoder.layers.31.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
392
+ "transformer.encoder.layers.31.self_attention.dense.weight": "model-00002-of-00003.safetensors",
393
+ "transformer.encoder.layers.31.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
394
+ "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
395
+ "transformer.encoder.layers.31.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
396
+ "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
397
+ "transformer.encoder.layers.31.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
398
+ "transformer.encoder.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
399
+ "transformer.encoder.layers.32.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
400
+ "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
401
+ "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
402
+ "transformer.encoder.layers.32.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
403
+ "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
404
+ "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
405
+ "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
406
+ "transformer.encoder.layers.32.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
407
+ "transformer.encoder.layers.32.self_attention.dense.weight": "model-00002-of-00003.safetensors",
408
+ "transformer.encoder.layers.32.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
409
+ "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
410
+ "transformer.encoder.layers.32.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
411
+ "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
412
+ "transformer.encoder.layers.32.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
413
+ "transformer.encoder.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
414
+ "transformer.encoder.layers.33.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
415
+ "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
416
+ "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
417
+ "transformer.encoder.layers.33.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
418
+ "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
419
+ "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
420
+ "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
421
+ "transformer.encoder.layers.33.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
422
+ "transformer.encoder.layers.33.self_attention.dense.weight": "model-00002-of-00003.safetensors",
423
+ "transformer.encoder.layers.33.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
424
+ "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
425
+ "transformer.encoder.layers.33.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
426
+ "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
427
+ "transformer.encoder.layers.33.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
428
+ "transformer.encoder.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
429
+ "transformer.encoder.layers.34.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
430
+ "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
431
+ "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
432
+ "transformer.encoder.layers.34.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
433
+ "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
434
+ "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
435
+ "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
436
+ "transformer.encoder.layers.34.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
437
+ "transformer.encoder.layers.34.self_attention.dense.weight": "model-00002-of-00003.safetensors",
438
+ "transformer.encoder.layers.34.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
439
+ "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
440
+ "transformer.encoder.layers.34.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
441
+ "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
442
+ "transformer.encoder.layers.34.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
443
+ "transformer.encoder.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
444
+ "transformer.encoder.layers.35.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
445
+ "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
446
+ "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
447
+ "transformer.encoder.layers.35.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
448
+ "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
449
+ "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
450
+ "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
451
+ "transformer.encoder.layers.35.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
452
+ "transformer.encoder.layers.35.self_attention.dense.weight": "model-00002-of-00003.safetensors",
453
+ "transformer.encoder.layers.35.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
454
+ "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
455
+ "transformer.encoder.layers.35.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
456
+ "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
457
+ "transformer.encoder.layers.35.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
458
+ "transformer.encoder.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
459
+ "transformer.encoder.layers.36.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
460
+ "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
461
+ "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
462
+ "transformer.encoder.layers.36.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
463
+ "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
464
+ "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
465
+ "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
466
+ "transformer.encoder.layers.36.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
467
+ "transformer.encoder.layers.36.self_attention.dense.weight": "model-00002-of-00003.safetensors",
468
+ "transformer.encoder.layers.36.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
469
+ "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
470
+ "transformer.encoder.layers.36.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
471
+ "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
472
+ "transformer.encoder.layers.36.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
473
+ "transformer.encoder.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
474
+ "transformer.encoder.layers.37.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
475
+ "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
476
+ "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
477
+ "transformer.encoder.layers.37.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
478
+ "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
479
+ "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
480
+ "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
481
+ "transformer.encoder.layers.37.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
482
+ "transformer.encoder.layers.37.self_attention.dense.weight": "model-00002-of-00003.safetensors",
483
+ "transformer.encoder.layers.37.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
484
+ "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
485
+ "transformer.encoder.layers.37.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
486
+ "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
487
+ "transformer.encoder.layers.37.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
488
+ "transformer.encoder.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
489
+ "transformer.encoder.layers.38.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
490
+ "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
491
+ "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
492
+ "transformer.encoder.layers.38.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
493
+ "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
494
+ "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
495
+ "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
496
+ "transformer.encoder.layers.38.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
497
+ "transformer.encoder.layers.38.self_attention.dense.weight": "model-00002-of-00003.safetensors",
498
+ "transformer.encoder.layers.38.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
499
+ "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
500
+ "transformer.encoder.layers.38.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
501
+ "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
502
+ "transformer.encoder.layers.38.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
503
+ "transformer.encoder.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
504
+ "transformer.encoder.layers.39.mlp.dense_4h_to_h.input_scale": "model-00002-of-00003.safetensors",
505
+ "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
506
+ "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00003.safetensors",
507
+ "transformer.encoder.layers.39.mlp.dense_h_to_4h.input_scale": "model-00002-of-00003.safetensors",
508
+ "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
509
+ "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00003.safetensors",
510
+ "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
511
+ "transformer.encoder.layers.39.self_attention.dense.input_scale": "model-00002-of-00003.safetensors",
512
+ "transformer.encoder.layers.39.self_attention.dense.weight": "model-00002-of-00003.safetensors",
513
+ "transformer.encoder.layers.39.self_attention.dense.weight_scale": "model-00002-of-00003.safetensors",
514
+ "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
515
+ "transformer.encoder.layers.39.self_attention.query_key_value.input_scale": "model-00002-of-00003.safetensors",
516
+ "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
517
+ "transformer.encoder.layers.39.self_attention.query_key_value.weight_scale": "model-00002-of-00003.safetensors",
518
+ "transformer.encoder.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
519
+ "transformer.encoder.layers.4.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
520
+ "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
521
+ "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
522
+ "transformer.encoder.layers.4.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
523
+ "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
524
+ "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
525
+ "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
526
+ "transformer.encoder.layers.4.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
527
+ "transformer.encoder.layers.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
528
+ "transformer.encoder.layers.4.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
529
+ "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
530
+ "transformer.encoder.layers.4.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
531
+ "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
532
+ "transformer.encoder.layers.4.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
533
+ "transformer.encoder.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
534
+ "transformer.encoder.layers.5.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
535
+ "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
536
+ "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
537
+ "transformer.encoder.layers.5.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
538
+ "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
539
+ "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
540
+ "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
541
+ "transformer.encoder.layers.5.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
542
+ "transformer.encoder.layers.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
543
+ "transformer.encoder.layers.5.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
544
+ "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
545
+ "transformer.encoder.layers.5.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
546
+ "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
547
+ "transformer.encoder.layers.5.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
548
+ "transformer.encoder.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
549
+ "transformer.encoder.layers.6.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
550
+ "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
551
+ "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
552
+ "transformer.encoder.layers.6.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
553
+ "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
554
+ "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
555
+ "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
556
+ "transformer.encoder.layers.6.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
557
+ "transformer.encoder.layers.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
558
+ "transformer.encoder.layers.6.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
559
+ "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
560
+ "transformer.encoder.layers.6.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
561
+ "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
562
+ "transformer.encoder.layers.6.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
563
+ "transformer.encoder.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
564
+ "transformer.encoder.layers.7.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
565
+ "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
566
+ "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
567
+ "transformer.encoder.layers.7.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
568
+ "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
569
+ "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
570
+ "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
571
+ "transformer.encoder.layers.7.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
572
+ "transformer.encoder.layers.7.self_attention.dense.weight": "model-00001-of-00003.safetensors",
573
+ "transformer.encoder.layers.7.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
574
+ "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
575
+ "transformer.encoder.layers.7.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
576
+ "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
577
+ "transformer.encoder.layers.7.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
578
+ "transformer.encoder.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
579
+ "transformer.encoder.layers.8.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
580
+ "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
581
+ "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
582
+ "transformer.encoder.layers.8.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
583
+ "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
584
+ "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
585
+ "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
586
+ "transformer.encoder.layers.8.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
587
+ "transformer.encoder.layers.8.self_attention.dense.weight": "model-00001-of-00003.safetensors",
588
+ "transformer.encoder.layers.8.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
589
+ "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
590
+ "transformer.encoder.layers.8.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
591
+ "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
592
+ "transformer.encoder.layers.8.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
593
+ "transformer.encoder.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
594
+ "transformer.encoder.layers.9.mlp.dense_4h_to_h.input_scale": "model-00001-of-00003.safetensors",
595
+ "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
596
+ "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00003.safetensors",
597
+ "transformer.encoder.layers.9.mlp.dense_h_to_4h.input_scale": "model-00001-of-00003.safetensors",
598
+ "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
599
+ "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00003.safetensors",
600
+ "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
601
+ "transformer.encoder.layers.9.self_attention.dense.input_scale": "model-00001-of-00003.safetensors",
602
+ "transformer.encoder.layers.9.self_attention.dense.weight": "model-00001-of-00003.safetensors",
603
+ "transformer.encoder.layers.9.self_attention.dense.weight_scale": "model-00001-of-00003.safetensors",
604
+ "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
605
+ "transformer.encoder.layers.9.self_attention.query_key_value.input_scale": "model-00001-of-00003.safetensors",
606
+ "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
607
+ "transformer.encoder.layers.9.self_attention.query_key_value.weight_scale": "model-00001-of-00003.safetensors",
608
+ "transformer.output_layer.weight": "model-00003-of-00003.safetensors",
609
+ "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00003.safetensors"
610
+ }
611
+ }
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
3
+ size 2623634
tokenizer_config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
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
+ "THUDM/glm-4-9b-chat--tokenization_chatglm.ChatGLM4Tokenizer",
135
+ null
136
+ ]
137
+ },
138
+ "chat_template": "[gMASK]<sop>{% for item in messages %}{% if item['tools'] is defined %}<|system|>\n你是一个名为 ChatGLM 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。\n\n# 可用工具{% set tools = item['tools'] %}{% for tool in tools %}{% if tool['type'] == 'function' %}\n\n## {{ tool['function']['name'] }}\n\n{{ tool['function'] | tojson(indent=4) }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。{% elif tool['type'] == 'python' %}\n\n## python\n\n当你向 `python` 发送包含 Python 代码的消息时，该代码将会在一个有状态的 Jupyter notebook 环境中执行。\n`python` 返回代码执行的输出，或在执行 60 秒后返回超时。\n`/mnt/data` 将会持久化存储你的文件。在此会话中，`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用，这些在线内容的访问将不会成功。{% elif tool['type'] == 'simple_browser' %}\n\n## simple_browser\n\n你可以使用 `simple_browser` 工具。该工具支持以下函数：\n`search(query: str, recency_days: int)`：使用搜索引擎进行查询并显示结果，可以使用 `recency_days` 参数控制搜索内容的时效性。\n`mclick(ids: list[int])`：获取一系列指定 id 的页面内容。每次调用时，须选择3-10个页面。选择多个角度的页面，同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的，你也可以多打开一些可能有用的页面而不用担心内容过多。\n`open_url(url: str)`：打开指定的 URL。\n\n使用 `【{引用 id}†{引用文本}】` 来引用内容。\n\n操作步骤：1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在回复中应当引用信息来源。\n 如果用户提供了 URL，也可��用 `open_url` 直接打开页面。\n如果初次搜索结果没有找到合适的信息，也可以再次使用 `search` 进行搜索。{% elif tool['type'] == 'cogview' %}\n\n## cogview\n\n如果用户的请求中包含了对图像的描述，你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述，规则：\n- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。\n- 应当尽可能详细地描述图像生成的需求，需求描述约 100 英文单词。\n- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。\n- 如无特殊说明，所在地为中国，持有中国立场并遵循中国社会主义价值观。{% endif %}{% endfor %}{% endif %}{% if item['content'] %}<|{{ item['role'] }}|>{{ item['metadata'] }}\n{{ item['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
139
+ "clean_up_tokenization_spaces": false,
140
+ "do_lower_case": false,
141
+ "eos_token": "<|endoftext|>",
142
+ "model_max_length": 128000,
143
+ "pad_token": "<|endoftext|>",
144
+ "padding_side": "left",
145
+ "remove_space": false,
146
+ "tokenizer_class": "ChatGLM4Tokenizer"
147
+ }