Upload folder using huggingface_hub
Browse files- added_tokens.json +16 -0
- config.json +50 -0
- generation_config.json +13 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +291 -0
- special_tokens_map.json +32 -0
- tokenizer.model +3 -0
- tokenizer_config.json +147 -0
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 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"rmsnorm": true,
|
43 |
+
"rope_ratio": 500,
|
44 |
+
"seq_length": 131072,
|
45 |
+
"tie_word_embeddings": false,
|
46 |
+
"torch_dtype": "bfloat16",
|
47 |
+
"transformers_version": "4.44.2",
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 151552
|
50 |
+
}
|
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": "4.44.2"
|
13 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f29788815ecf80361c159b371875aee7a76cab85a2c5eb4ef4b2215a3cc8502
|
3 |
+
size 4984147224
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e0972040dba2d7d9ed00703f04cc2369211bcf6fef61bb8e62861829130f420
|
3 |
+
size 4895071360
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9b290a98bd90cc938353369e54742f7ce2cfff1c95756c0759f716a43927cec
|
3 |
+
size 4895071384
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39e4715268151af6c5bf8719130ea7dc2acab0b729104f75e4c3e1ec0f8891af
|
3 |
+
size 4025651256
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,291 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 18799902784
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"transformer.embedding.word_embeddings.weight": "model-00001-of-00004.safetensors",
|
7 |
+
"transformer.encoder.final_layernorm.weight": "model-00004-of-00004.safetensors",
|
8 |
+
"transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
14 |
+
"transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
21 |
+
"transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"transformer.encoder.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
23 |
+
"transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
24 |
+
"transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
25 |
+
"transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
26 |
+
"transformer.encoder.layers.10.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
28 |
+
"transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"transformer.encoder.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"transformer.encoder.layers.11.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
35 |
+
"transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"transformer.encoder.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"transformer.encoder.layers.12.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
42 |
+
"transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"transformer.encoder.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"transformer.encoder.layers.13.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
49 |
+
"transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"transformer.encoder.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"transformer.encoder.layers.14.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
56 |
+
"transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"transformer.encoder.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"transformer.encoder.layers.15.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
63 |
+
"transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"transformer.encoder.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"transformer.encoder.layers.16.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
70 |
+
"transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"transformer.encoder.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
74 |
+
"transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"transformer.encoder.layers.17.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
77 |
+
"transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"transformer.encoder.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"transformer.encoder.layers.18.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
84 |
+
"transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"transformer.encoder.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
86 |
+
"transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
89 |
+
"transformer.encoder.layers.19.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
91 |
+
"transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
93 |
+
"transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
94 |
+
"transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
95 |
+
"transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
96 |
+
"transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
97 |
+
"transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
98 |
+
"transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
99 |
+
"transformer.encoder.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
100 |
+
"transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
101 |
+
"transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
102 |
+
"transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
103 |
+
"transformer.encoder.layers.20.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
104 |
+
"transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
105 |
+
"transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
106 |
+
"transformer.encoder.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
107 |
+
"transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
108 |
+
"transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
109 |
+
"transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
110 |
+
"transformer.encoder.layers.21.self_attention.dense.weight": "model-00002-of-00004.safetensors",
|
111 |
+
"transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
112 |
+
"transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
113 |
+
"transformer.encoder.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
114 |
+
"transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
115 |
+
"transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
116 |
+
"transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
117 |
+
"transformer.encoder.layers.22.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
118 |
+
"transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
119 |
+
"transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
120 |
+
"transformer.encoder.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
121 |
+
"transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
122 |
+
"transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
123 |
+
"transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
124 |
+
"transformer.encoder.layers.23.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
125 |
+
"transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
126 |
+
"transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
127 |
+
"transformer.encoder.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
128 |
+
"transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
131 |
+
"transformer.encoder.layers.24.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
132 |
+
"transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
133 |
+
"transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
134 |
+
"transformer.encoder.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
137 |
+
"transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"transformer.encoder.layers.25.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
140 |
+
"transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"transformer.encoder.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"transformer.encoder.layers.26.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
147 |
+
"transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"transformer.encoder.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
149 |
+
"transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
151 |
+
"transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"transformer.encoder.layers.27.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
154 |
+
"transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"transformer.encoder.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"transformer.encoder.layers.28.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
161 |
+
"transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
162 |
+
"transformer.encoder.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
163 |
+
"transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
164 |
+
"transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"transformer.encoder.layers.29.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
168 |
+
"transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
170 |
+
"transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
171 |
+
"transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
172 |
+
"transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
173 |
+
"transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
174 |
+
"transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
175 |
+
"transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
176 |
+
"transformer.encoder.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"transformer.encoder.layers.30.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
182 |
+
"transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"transformer.encoder.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
185 |
+
"transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
187 |
+
"transformer.encoder.layers.31.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
189 |
+
"transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
190 |
+
"transformer.encoder.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
192 |
+
"transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
193 |
+
"transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
194 |
+
"transformer.encoder.layers.32.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
196 |
+
"transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
197 |
+
"transformer.encoder.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
198 |
+
"transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
|
199 |
+
"transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
|
200 |
+
"transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
201 |
+
"transformer.encoder.layers.33.self_attention.dense.weight": "model-00003-of-00004.safetensors",
|
202 |
+
"transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
203 |
+
"transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
204 |
+
"transformer.encoder.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
205 |
+
"transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
|
206 |
+
"transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
|
207 |
+
"transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
208 |
+
"transformer.encoder.layers.34.self_attention.dense.weight": "model-00004-of-00004.safetensors",
|
209 |
+
"transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
|
210 |
+
"transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
|
211 |
+
"transformer.encoder.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
212 |
+
"transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
|
213 |
+
"transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
|
214 |
+
"transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
215 |
+
"transformer.encoder.layers.35.self_attention.dense.weight": "model-00004-of-00004.safetensors",
|
216 |
+
"transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
|
217 |
+
"transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
|
218 |
+
"transformer.encoder.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
219 |
+
"transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
|
220 |
+
"transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
|
221 |
+
"transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
222 |
+
"transformer.encoder.layers.36.self_attention.dense.weight": "model-00004-of-00004.safetensors",
|
223 |
+
"transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
|
224 |
+
"transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
|
225 |
+
"transformer.encoder.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
226 |
+
"transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
|
227 |
+
"transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
|
228 |
+
"transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
229 |
+
"transformer.encoder.layers.37.self_attention.dense.weight": "model-00004-of-00004.safetensors",
|
230 |
+
"transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
|
231 |
+
"transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
|
232 |
+
"transformer.encoder.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
233 |
+
"transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
|
234 |
+
"transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
|
235 |
+
"transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
236 |
+
"transformer.encoder.layers.38.self_attention.dense.weight": "model-00004-of-00004.safetensors",
|
237 |
+
"transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
|
238 |
+
"transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
|
239 |
+
"transformer.encoder.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
240 |
+
"transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
|
241 |
+
"transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
|
242 |
+
"transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
243 |
+
"transformer.encoder.layers.39.self_attention.dense.weight": "model-00004-of-00004.safetensors",
|
244 |
+
"transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
|
245 |
+
"transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
|
246 |
+
"transformer.encoder.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
247 |
+
"transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
248 |
+
"transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
249 |
+
"transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
250 |
+
"transformer.encoder.layers.4.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
251 |
+
"transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
252 |
+
"transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
253 |
+
"transformer.encoder.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
254 |
+
"transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
255 |
+
"transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
256 |
+
"transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
257 |
+
"transformer.encoder.layers.5.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
258 |
+
"transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
259 |
+
"transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
260 |
+
"transformer.encoder.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
261 |
+
"transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
262 |
+
"transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
263 |
+
"transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
264 |
+
"transformer.encoder.layers.6.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
265 |
+
"transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
266 |
+
"transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
267 |
+
"transformer.encoder.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
268 |
+
"transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
269 |
+
"transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
270 |
+
"transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
271 |
+
"transformer.encoder.layers.7.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
272 |
+
"transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
273 |
+
"transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
274 |
+
"transformer.encoder.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
275 |
+
"transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
276 |
+
"transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
277 |
+
"transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
278 |
+
"transformer.encoder.layers.8.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
279 |
+
"transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
280 |
+
"transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
281 |
+
"transformer.encoder.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
282 |
+
"transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
283 |
+
"transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
284 |
+
"transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
285 |
+
"transformer.encoder.layers.9.self_attention.dense.weight": "model-00001-of-00004.safetensors",
|
286 |
+
"transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
287 |
+
"transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
288 |
+
"transformer.output_layer.weight": "model-00004-of-00004.safetensors",
|
289 |
+
"transformer.rotary_pos_emb.inv_freq": "model-00001-of-00004.safetensors"
|
290 |
+
}
|
291 |
+
}
|
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 |
+
}
|