qiuhuachuan
commited on
Commit
•
e18b6c6
1
Parent(s):
95a1997
Upload 13 files
Browse files- config.json +46 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00007.bin +3 -0
- pytorch_model-00002-of-00007.bin +3 -0
- pytorch_model-00003-of-00007.bin +3 -0
- pytorch_model-00004-of-00007.bin +3 -0
- pytorch_model-00005-of-00007.bin +3 -0
- pytorch_model-00006-of-00007.bin +3 -0
- pytorch_model-00007-of-00007.bin +3 -0
- pytorch_model.bin.index.json +207 -0
- special_tokens_map.json +1 -0
- tokenizer.model +3 -0
- tokenizer_config.json +14 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "THUDM/chatglm2-6b",
|
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/chatglm2-6b--configuration_chatglm.ChatGLMConfig",
|
14 |
+
"AutoModel": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
|
15 |
+
"AutoModelForCausalLM": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
|
16 |
+
"AutoModelForSeq2SeqLM": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
|
17 |
+
"AutoModelForSequenceClassification": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForSequenceClassification"
|
18 |
+
},
|
19 |
+
"bias_dropout_fusion": true,
|
20 |
+
"eos_token_id": 2,
|
21 |
+
"ffn_hidden_size": 13696,
|
22 |
+
"fp32_residual_connection": false,
|
23 |
+
"hidden_dropout": 0.0,
|
24 |
+
"hidden_size": 4096,
|
25 |
+
"kv_channels": 128,
|
26 |
+
"layernorm_epsilon": 1e-05,
|
27 |
+
"model_type": "chatglm",
|
28 |
+
"multi_query_attention": true,
|
29 |
+
"multi_query_group_num": 2,
|
30 |
+
"num_attention_heads": 32,
|
31 |
+
"num_layers": 28,
|
32 |
+
"original_rope": true,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"padded_vocab_size": 65024,
|
35 |
+
"post_layer_norm": true,
|
36 |
+
"pre_seq_len": null,
|
37 |
+
"prefix_projection": false,
|
38 |
+
"quantization_bit": 0,
|
39 |
+
"rmsnorm": true,
|
40 |
+
"seq_length": 32768,
|
41 |
+
"tie_word_embeddings": false,
|
42 |
+
"torch_dtype": "float16",
|
43 |
+
"transformers_version": "4.30.2",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 65024
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
+
}
|
pytorch_model-00001-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4640f5dc0add0dba0164da454e5b18c22602c23a31735e9405b18c887c5e950d
|
3 |
+
size 1827780295
|
pytorch_model-00002-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12839a571a6b026a2af81dcd6b23e821e1282fb1e53a569aec790b6edae1a0da
|
3 |
+
size 1968298621
|
pytorch_model-00003-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dab13b5c676e6e2e708625cc1cc662d61d2fd631d0e68869baf5881306fd875
|
3 |
+
size 1927414113
|
pytorch_model-00004-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcf45596997ccc3036bca3d5ba2a2f5805aeb80c5c2b54c32b69640318f22803
|
3 |
+
size 1815225011
|
pytorch_model-00005-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a07cc37377579545d696492f1faaed86ed544f64d975bd48725d4d7fcc6dbfe7
|
3 |
+
size 1968298621
|
pytorch_model-00006-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eece97c4eca8daf67200f03bbc5eac60a46cf04c100f060e288f827829aa170
|
3 |
+
size 1927414113
|
pytorch_model-00007-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d4ec56df02178ca182969ad68c1f019e5ec973a556927864414496768ff7bf5
|
3 |
+
size 1052808003
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 12487168064
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00007.bin",
|
7 |
+
"transformer.encoder.final_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
8 |
+
"transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
9 |
+
"transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
|
10 |
+
"transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
|
11 |
+
"transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
12 |
+
"transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
|
13 |
+
"transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
|
14 |
+
"transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
|
15 |
+
"transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
16 |
+
"transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
|
17 |
+
"transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
|
18 |
+
"transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
19 |
+
"transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
|
20 |
+
"transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
|
21 |
+
"transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
|
22 |
+
"transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
23 |
+
"transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
|
24 |
+
"transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
25 |
+
"transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
26 |
+
"transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
27 |
+
"transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
28 |
+
"transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
29 |
+
"transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
30 |
+
"transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
|
31 |
+
"transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
32 |
+
"transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
33 |
+
"transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
34 |
+
"transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
35 |
+
"transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
36 |
+
"transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
37 |
+
"transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
38 |
+
"transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
39 |
+
"transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
40 |
+
"transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
41 |
+
"transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
42 |
+
"transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
43 |
+
"transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
44 |
+
"transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
45 |
+
"transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
|
46 |
+
"transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
47 |
+
"transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
48 |
+
"transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
49 |
+
"transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
50 |
+
"transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
51 |
+
"transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
52 |
+
"transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
|
53 |
+
"transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
54 |
+
"transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
55 |
+
"transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
56 |
+
"transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
57 |
+
"transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
58 |
+
"transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
59 |
+
"transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
|
60 |
+
"transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
61 |
+
"transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
62 |
+
"transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
63 |
+
"transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
64 |
+
"transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
65 |
+
"transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
66 |
+
"transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
|
67 |
+
"transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
68 |
+
"transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
69 |
+
"transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
70 |
+
"transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
71 |
+
"transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
72 |
+
"transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
73 |
+
"transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
74 |
+
"transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
75 |
+
"transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
76 |
+
"transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
77 |
+
"transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
78 |
+
"transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
79 |
+
"transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
80 |
+
"transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
81 |
+
"transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
82 |
+
"transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
|
83 |
+
"transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
|
84 |
+
"transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
|
85 |
+
"transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
86 |
+
"transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
87 |
+
"transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
88 |
+
"transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
89 |
+
"transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
|
90 |
+
"transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
|
91 |
+
"transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
|
92 |
+
"transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
93 |
+
"transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
|
94 |
+
"transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
|
95 |
+
"transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
96 |
+
"transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
|
97 |
+
"transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
|
98 |
+
"transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
|
99 |
+
"transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
100 |
+
"transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
101 |
+
"transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
102 |
+
"transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
103 |
+
"transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
|
104 |
+
"transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
|
105 |
+
"transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
|
106 |
+
"transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
107 |
+
"transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
108 |
+
"transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
109 |
+
"transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
110 |
+
"transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
|
111 |
+
"transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
|
112 |
+
"transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
|
113 |
+
"transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
114 |
+
"transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
|
115 |
+
"transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
116 |
+
"transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
117 |
+
"transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
118 |
+
"transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
119 |
+
"transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
120 |
+
"transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
121 |
+
"transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
|
122 |
+
"transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
123 |
+
"transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
124 |
+
"transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
125 |
+
"transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
126 |
+
"transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
127 |
+
"transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
128 |
+
"transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
|
129 |
+
"transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
130 |
+
"transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
131 |
+
"transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
132 |
+
"transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
133 |
+
"transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
134 |
+
"transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
135 |
+
"transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
|
136 |
+
"transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
137 |
+
"transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
138 |
+
"transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
139 |
+
"transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
140 |
+
"transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
141 |
+
"transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
142 |
+
"transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
|
143 |
+
"transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
144 |
+
"transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
145 |
+
"transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
146 |
+
"transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
147 |
+
"transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
148 |
+
"transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
149 |
+
"transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
|
150 |
+
"transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
|
151 |
+
"transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
152 |
+
"transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
|
153 |
+
"transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
|
154 |
+
"transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
|
155 |
+
"transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
156 |
+
"transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
157 |
+
"transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
158 |
+
"transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
159 |
+
"transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
|
160 |
+
"transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
|
161 |
+
"transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
|
162 |
+
"transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
163 |
+
"transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
164 |
+
"transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
165 |
+
"transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
166 |
+
"transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
|
167 |
+
"transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
|
168 |
+
"transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
|
169 |
+
"transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
170 |
+
"transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
171 |
+
"transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
172 |
+
"transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
173 |
+
"transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
|
174 |
+
"transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
|
175 |
+
"transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
|
176 |
+
"transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
177 |
+
"transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
178 |
+
"transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
179 |
+
"transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
180 |
+
"transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
|
181 |
+
"transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
|
182 |
+
"transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
|
183 |
+
"transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
184 |
+
"transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
185 |
+
"transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
186 |
+
"transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
187 |
+
"transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
|
188 |
+
"transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
|
189 |
+
"transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
|
190 |
+
"transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
191 |
+
"transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
|
192 |
+
"transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
193 |
+
"transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
194 |
+
"transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
195 |
+
"transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
196 |
+
"transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
197 |
+
"transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
198 |
+
"transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
|
199 |
+
"transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
200 |
+
"transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
201 |
+
"transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
202 |
+
"transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
203 |
+
"transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
204 |
+
"transformer.output_layer.weight": "pytorch_model-00007-of-00007.bin",
|
205 |
+
"transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00007.bin"
|
206 |
+
}
|
207 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoTokenizer": [
|
4 |
+
"THUDM/chatglm2-6b--tokenization_chatglm.ChatGLMTokenizer",
|
5 |
+
null
|
6 |
+
]
|
7 |
+
},
|
8 |
+
"clean_up_tokenization_spaces": true,
|
9 |
+
"do_lower_case": false,
|
10 |
+
"model_max_length": 1000000000000000019884624838656,
|
11 |
+
"padding_side": "left",
|
12 |
+
"remove_space": false,
|
13 |
+
"tokenizer_class": "ChatGLMTokenizer"
|
14 |
+
}
|