Sunanhe commited on
Commit
94dc881
1 Parent(s): a577a68

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 64006,
3
+ "</quad>": 64002,
4
+ "</ref>": 64004,
5
+ "<IMG_CONTEXT>": 64000,
6
+ "<box>": 64005,
7
+ "<quad>": 64001,
8
+ "<ref>": 64003
9
+ }
config.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/scratch/lsmodhealth/shebd/1_Pretrained/InternVL-Chat-Chinese-V1-2-Plus",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel"
10
+ },
11
+ "downsample_ratio": 0.5,
12
+ "force_image_size": 448,
13
+ "llm_config": {
14
+ "_name_or_path": "01-ai/Yi-34B",
15
+ "add_cross_attention": false,
16
+ "architectures": [
17
+ "LlamaForCausalLM"
18
+ ],
19
+ "attention_bias": false,
20
+ "attention_dropout": 0.0,
21
+ "attn_implementation": "flash_attention_2",
22
+ "bad_words_ids": null,
23
+ "begin_suppress_tokens": null,
24
+ "bos_token_id": 1,
25
+ "chunk_size_feed_forward": 0,
26
+ "cross_attention_hidden_size": null,
27
+ "decoder_start_token_id": null,
28
+ "diversity_penalty": 0.0,
29
+ "do_sample": false,
30
+ "early_stopping": false,
31
+ "encoder_no_repeat_ngram_size": 0,
32
+ "eos_token_id": 7,
33
+ "exponential_decay_length_penalty": null,
34
+ "finetuning_task": null,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": null,
37
+ "hidden_act": "silu",
38
+ "hidden_size": 7168,
39
+ "id2label": {
40
+ "0": "LABEL_0",
41
+ "1": "LABEL_1"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 20480,
45
+ "is_decoder": false,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 4096,
54
+ "min_length": 0,
55
+ "model_type": "llama",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_attention_heads": 56,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_hidden_layers": 60,
61
+ "num_key_value_heads": 8,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 0,
67
+ "prefix": null,
68
+ "pretraining_tp": 1,
69
+ "problem_type": null,
70
+ "pruned_heads": {},
71
+ "remove_invalid_values": false,
72
+ "repetition_penalty": 1.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "rms_norm_eps": 1e-05,
76
+ "rope_scaling": null,
77
+ "rope_theta": 5000000.0,
78
+ "sep_token_id": null,
79
+ "suppress_tokens": null,
80
+ "task_specific_params": null,
81
+ "temperature": 1.0,
82
+ "tf_legacy_loss": false,
83
+ "tie_encoder_decoder": false,
84
+ "tie_word_embeddings": false,
85
+ "tokenizer_class": null,
86
+ "top_k": 50,
87
+ "top_p": 1.0,
88
+ "torch_dtype": "bfloat16",
89
+ "torchscript": false,
90
+ "transformers_version": "4.38.2",
91
+ "typical_p": 1.0,
92
+ "use_bfloat16": false,
93
+ "use_cache": false,
94
+ "vocab_size": 64007
95
+ },
96
+ "model_type": "internvl_chat",
97
+ "pad2square": false,
98
+ "select_layer": -1,
99
+ "template": "Hermes-2",
100
+ "torch_dtype": "bfloat16",
101
+ "transformers_version": null,
102
+ "use_backbone_lora": 0,
103
+ "use_llm_lora": 16,
104
+ "vision_config": {
105
+ "_name_or_path": "",
106
+ "add_cross_attention": false,
107
+ "architectures": [
108
+ "InternVisionModel"
109
+ ],
110
+ "attention_dropout": 0.0,
111
+ "bad_words_ids": null,
112
+ "begin_suppress_tokens": null,
113
+ "bos_token_id": null,
114
+ "chunk_size_feed_forward": 0,
115
+ "cross_attention_hidden_size": null,
116
+ "decoder_start_token_id": null,
117
+ "diversity_penalty": 0.0,
118
+ "do_sample": false,
119
+ "drop_path_rate": 0.0,
120
+ "dropout": 0.0,
121
+ "early_stopping": false,
122
+ "encoder_no_repeat_ngram_size": 0,
123
+ "eos_token_id": null,
124
+ "exponential_decay_length_penalty": null,
125
+ "finetuning_task": null,
126
+ "forced_bos_token_id": null,
127
+ "forced_eos_token_id": null,
128
+ "hidden_act": "gelu",
129
+ "hidden_size": 3200,
130
+ "id2label": {
131
+ "0": "LABEL_0",
132
+ "1": "LABEL_1"
133
+ },
134
+ "image_size": 448,
135
+ "initializer_factor": 0.1,
136
+ "initializer_range": 1e-10,
137
+ "intermediate_size": 12800,
138
+ "is_decoder": false,
139
+ "is_encoder_decoder": false,
140
+ "label2id": {
141
+ "LABEL_0": 0,
142
+ "LABEL_1": 1
143
+ },
144
+ "layer_norm_eps": 1e-06,
145
+ "length_penalty": 1.0,
146
+ "max_length": 20,
147
+ "min_length": 0,
148
+ "model_type": "intern_vit_6b",
149
+ "no_repeat_ngram_size": 0,
150
+ "num_attention_heads": 25,
151
+ "num_beam_groups": 1,
152
+ "num_beams": 1,
153
+ "num_channels": 3,
154
+ "num_hidden_layers": 45,
155
+ "num_return_sequences": 1,
156
+ "output_attentions": false,
157
+ "output_hidden_states": false,
158
+ "output_scores": false,
159
+ "pad_token_id": null,
160
+ "patch_size": 14,
161
+ "prefix": null,
162
+ "problem_type": null,
163
+ "pruned_heads": {},
164
+ "qk_normalization": true,
165
+ "qkv_bias": false,
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "sep_token_id": null,
171
+ "suppress_tokens": null,
172
+ "task_specific_params": null,
173
+ "temperature": 1.0,
174
+ "tf_legacy_loss": false,
175
+ "tie_encoder_decoder": false,
176
+ "tie_word_embeddings": true,
177
+ "tokenizer_class": null,
178
+ "top_k": 50,
179
+ "top_p": 1.0,
180
+ "torch_dtype": "bfloat16",
181
+ "torchscript": false,
182
+ "transformers_version": "4.38.2",
183
+ "typical_p": 1.0,
184
+ "use_bfloat16": true,
185
+ "use_flash_attn": true
186
+ }
187
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.38.2"
4
+ }
model-00001-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6790717e7b97dcb470952c13eedd34e4f2a57899fd45111bc0d60fd3db1c2d4
3
+ size 4988569440
model-00002-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febc55c70089905c5d5c177c89906b77a179cc9aef8b9650d482e678555f0d05
3
+ size 4937253584
model-00003-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb6e656818e5658c29be5d11cf6463beae8dc5e08db14fc6bf25b252b7bb38e
3
+ size 4835281072
model-00004-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7ff7384e833358a1bd01123fe674924664b8d5ccc24b4cf9ef0cd24615135b
3
+ size 4773739256
model-00005-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9414b0893d626292e63ba97c4daef3397615832dbcc2f9560e7185bf723def
3
+ size 4906873328
model-00006-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46ed54b1bf8b838622a58f1c070218b05c5eaeac4ccee64646193cb4d48aab41
3
+ size 4876959040
model-00007-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f7ed0363a198209d0e68d7da377e3a47e479e9c42996ede3b7f2b4e42edb2a
3
+ size 4773739352
model-00008-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31928887e76e80a624a36a46618ef7fab2e0b47c0d4aac7dfdd5445aacf813d5
3
+ size 4906873408
model-00009-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6774c7a893b11f4d26bf1a56869540db9ab3b46d43d8ab45a595cd7c13e9f212
3
+ size 4876959040
model-00010-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89002a53e53e103025a4158e4416f45ba306af638a8af5a4fd7c7e653420d04
3
+ size 4773739352
model-00011-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec8766793be2e08bbfaa73db24f15fc5fdb5e029aaaeba4197bd309e83a1786
3
+ size 4906873408
model-00012-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaabc2d9546814cccad115763a709c312a77941bd7398ac8f4a431c63ec9e22f
3
+ size 4876959040
model-00013-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e74a4e0298d43285e8b86ac91fd2a623dc0a24975ade346269ebc786c270054
3
+ size 4773739352
model-00014-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c2e0e9d72f417ff16a581453eb927aff1bd7475910e48360ac1ba76c68b86b
3
+ size 4906873408
model-00015-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7bf27781ba993f0415eea824d9505fe052c43f7ad844e0cdc8abcbd2f3bf116
3
+ size 4876959040
model-00016-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a2ffa7398bf672593dbe58744b7a145ec4b0f221d5ff4df634333d812db2ed
3
+ size 4773739352
model-00017-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ce7138477312c01e1c67479dc7090139e3762ee4c9890f6154ee67edcc04cd
3
+ size 2618289296
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<img>",
4
+ "</img>",
5
+ "<IMG_CONTEXT>",
6
+ "<quad>",
7
+ "</quad>",
8
+ "<ref>",
9
+ "</ref>",
10
+ "<box>",
11
+ "</box>"
12
+ ],
13
+ "bos_token": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "unk_token": {
35
+ "content": "<unk>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|startoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "6": {
31
+ "content": "<|im_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "7": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "68": {
47
+ "content": "<img>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "70": {
55
+ "content": "</img>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "64000": {
63
+ "content": "<IMG_CONTEXT>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "64001": {
71
+ "content": "<quad>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "64002": {
79
+ "content": "</quad>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "64003": {
87
+ "content": "<ref>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "64004": {
95
+ "content": "</ref>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "64005": {
103
+ "content": "<box>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "64006": {
111
+ "content": "</box>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "additional_special_tokens": [
120
+ "<img>",
121
+ "</img>",
122
+ "<IMG_CONTEXT>",
123
+ "<quad>",
124
+ "</quad>",
125
+ "<ref>",
126
+ "</ref>",
127
+ "<box>",
128
+ "</box>"
129
+ ],
130
+ "bos_token": "<|startoftext|>",
131
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
132
+ "clean_up_tokenization_spaces": false,
133
+ "eos_token": "<|im_end|>",
134
+ "legacy": true,
135
+ "model_max_length": 2048,
136
+ "pad_token": "<unk>",
137
+ "sp_model_kwargs": {},
138
+ "spaces_between_special_tokens": false,
139
+ "tokenizer_class": "LlamaTokenizer",
140
+ "trust_remote_code": false,
141
+ "unk_token": "<unk>",
142
+ "use_default_system_prompt": false,
143
+ "use_fast": true
144
+ }