Hugging Face's logo

BK-Lee
/
TroL-3.8B

Text Generation
Transformers
Safetensors
trol
conversational
Inference Endpoints
Model card Files Community
BK-Lee commited on
Commit
065bb14
•
1 Parent(s): 54360f3

Upload 8 files

Browse files
Files changed (8) hide show
  1. added_tokens.json +22 -0
  2. config.json +296 -0
  3. generation_config.json +4 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +41 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +215 -0
added_tokens.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 32019,
3
+ "</img>": 32012,
4
+ "</quad>": 32015,
5
+ "</ref>": 32017,
6
+ "<IMG_CONTEXT>": 32013,
7
+ "<box>": 32018,
8
+ "<img>": 32011,
9
+ "<quad>": 32014,
10
+ "<ref>": 32016,
11
+ "<|assistant|>": 32001,
12
+ "<|endoftext|>": 32000,
13
+ "<|end|>": 32007,
14
+ "<|placeholder1|>": 32002,
15
+ "<|placeholder2|>": 32003,
16
+ "<|placeholder3|>": 32004,
17
+ "<|placeholder4|>": 32005,
18
+ "<|placeholder5|>": 32008,
19
+ "<|placeholder6|>": 32009,
20
+ "<|system|>": 32006,
21
+ "<|user|>": 32010
22
+ }
config.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "6f97087daec17e4b033d4d846c0b64c09c4268cd",
3
+ "_name_or_path": "/mnt/ssd/lbk-cvpr/checkpoints/models--phi3-3.8b/snapshots/6f97087daec17e4b033d4d846c0b64c09c4268cd",
4
+ "architectures": [
5
+ "TroLForCausalLM"
6
+ ],
7
+ "downsample_ratio": 0.5,
8
+ "dynamic_image_size": true,
9
+ "eos_token_id": 2,
10
+ "force_image_size": 448,
11
+ "ignore_index": -100,
12
+ "image_token_index": 32013,
13
+ "llm_config": {
14
+ "_name_or_path": "",
15
+ "add_cross_attention": false,
16
+ "architectures": [
17
+ "Phi3ForCausalLM"
18
+ ],
19
+ "attention_dropout": 0.0,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": 1,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "embd_pdrop": 0.0,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 32000,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "hidden_act": "silu",
37
+ "hidden_size": 3072,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 8192,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1
49
+ },
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "max_position_embeddings": 131072,
53
+ "min_length": 0,
54
+ "model_type": "phi3",
55
+ "no_repeat_ngram_size": 0,
56
+ "num_attention_heads": 32,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 32,
60
+ "num_key_value_heads": 32,
61
+ "num_return_sequences": 1,
62
+ "original_max_position_embeddings": 4096,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 32000,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "resid_pdrop": 0.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "rms_norm_eps": 1e-05,
76
+ "rope_scaling": {
77
+ "long_factor": [
78
+ 1.0299999713897705,
79
+ 1.0499999523162842,
80
+ 1.0499999523162842,
81
+ 1.0799999237060547,
82
+ 1.2299998998641968,
83
+ 1.2299998998641968,
84
+ 1.2999999523162842,
85
+ 1.4499999284744263,
86
+ 1.5999999046325684,
87
+ 1.6499998569488525,
88
+ 1.8999998569488525,
89
+ 2.859999895095825,
90
+ 3.68999981880188,
91
+ 5.419999599456787,
92
+ 5.489999771118164,
93
+ 5.489999771118164,
94
+ 9.09000015258789,
95
+ 11.579999923706055,
96
+ 15.65999984741211,
97
+ 15.769999504089355,
98
+ 15.789999961853027,
99
+ 18.360000610351562,
100
+ 21.989999771118164,
101
+ 23.079999923706055,
102
+ 30.009998321533203,
103
+ 32.35000228881836,
104
+ 32.590003967285156,
105
+ 35.56000518798828,
106
+ 39.95000457763672,
107
+ 53.840003967285156,
108
+ 56.20000457763672,
109
+ 57.95000457763672,
110
+ 59.29000473022461,
111
+ 59.77000427246094,
112
+ 59.920005798339844,
113
+ 61.190006256103516,
114
+ 61.96000671386719,
115
+ 62.50000762939453,
116
+ 63.3700065612793,
117
+ 63.48000717163086,
118
+ 63.48000717163086,
119
+ 63.66000747680664,
120
+ 63.850006103515625,
121
+ 64.08000946044922,
122
+ 64.760009765625,
123
+ 64.80001068115234,
124
+ 64.81001281738281,
125
+ 64.81001281738281
126
+ ],
127
+ "short_factor": [
128
+ 1.05,
129
+ 1.05,
130
+ 1.05,
131
+ 1.1,
132
+ 1.1,
133
+ 1.1500000000000001,
134
+ 1.2000000000000002,
135
+ 1.2500000000000002,
136
+ 1.3000000000000003,
137
+ 1.3500000000000003,
138
+ 1.5000000000000004,
139
+ 2.000000000000001,
140
+ 2.000000000000001,
141
+ 2.000000000000001,
142
+ 2.000000000000001,
143
+ 2.000000000000001,
144
+ 2.000000000000001,
145
+ 2.000000000000001,
146
+ 2.000000000000001,
147
+ 2.000000000000001,
148
+ 2.000000000000001,
149
+ 2.000000000000001,
150
+ 2.000000000000001,
151
+ 2.000000000000001,
152
+ 2.000000000000001,
153
+ 2.000000000000001,
154
+ 2.000000000000001,
155
+ 2.000000000000001,
156
+ 2.000000000000001,
157
+ 2.000000000000001,
158
+ 2.000000000000001,
159
+ 2.000000000000001,
160
+ 2.0500000000000007,
161
+ 2.0500000000000007,
162
+ 2.0500000000000007,
163
+ 2.1000000000000005,
164
+ 2.1000000000000005,
165
+ 2.1000000000000005,
166
+ 2.1500000000000004,
167
+ 2.1500000000000004,
168
+ 2.3499999999999996,
169
+ 2.549999999999999,
170
+ 2.5999999999999988,
171
+ 2.5999999999999988,
172
+ 2.7499999999999982,
173
+ 2.849999999999998,
174
+ 2.849999999999998,
175
+ 2.9499999999999975
176
+ ],
177
+ "type": "su"
178
+ },
179
+ "rope_theta": 10000.0,
180
+ "sep_token_id": null,
181
+ "sliding_window": 262144,
182
+ "suppress_tokens": null,
183
+ "task_specific_params": null,
184
+ "temperature": 1.0,
185
+ "tf_legacy_loss": false,
186
+ "tie_encoder_decoder": false,
187
+ "tie_word_embeddings": false,
188
+ "tokenizer_class": null,
189
+ "top_k": 50,
190
+ "top_p": 1.0,
191
+ "torch_dtype": "bfloat16",
192
+ "torchscript": false,
193
+ "transformers_version": "4.41.2",
194
+ "typical_p": 1.0,
195
+ "use_bfloat16": false,
196
+ "use_cache": false,
197
+ "vocab_size": 32020
198
+ },
199
+ "max_dynamic_patch": 12,
200
+ "min_dynamic_patch": 1,
201
+ "model_type": "trol",
202
+ "pad2square": false,
203
+ "pad_token_id": 2,
204
+ "ps_version": "v2",
205
+ "select_layer": -1,
206
+ "template": "phi3-chat",
207
+ "torch_dtype": "float16",
208
+ "transformers_version": null,
209
+ "use_backbone_lora": 0,
210
+ "use_llm_lora": 0,
211
+ "use_thumbnail": true,
212
+ "vision_config": {
213
+ "_name_or_path": "",
214
+ "add_cross_attention": false,
215
+ "architectures": [
216
+ "InternVisionModel"
217
+ ],
218
+ "attention_dropout": 0.0,
219
+ "bad_words_ids": null,
220
+ "begin_suppress_tokens": null,
221
+ "bos_token_id": null,
222
+ "chunk_size_feed_forward": 0,
223
+ "cross_attention_hidden_size": null,
224
+ "decoder_start_token_id": null,
225
+ "diversity_penalty": 0.0,
226
+ "do_sample": false,
227
+ "drop_path_rate": 0.1,
228
+ "dropout": 0.0,
229
+ "early_stopping": false,
230
+ "encoder_no_repeat_ngram_size": 0,
231
+ "eos_token_id": null,
232
+ "exponential_decay_length_penalty": null,
233
+ "finetuning_task": null,
234
+ "forced_bos_token_id": null,
235
+ "forced_eos_token_id": null,
236
+ "hidden_act": "gelu",
237
+ "hidden_size": 1024,
238
+ "id2label": {
239
+ "0": "LABEL_0",
240
+ "1": "LABEL_1"
241
+ },
242
+ "image_size": 448,
243
+ "initializer_factor": 1.0,
244
+ "initializer_range": 0.02,
245
+ "intermediate_size": 4096,
246
+ "is_decoder": false,
247
+ "is_encoder_decoder": false,
248
+ "label2id": {
249
+ "LABEL_0": 0,
250
+ "LABEL_1": 1
251
+ },
252
+ "layer_norm_eps": 1e-06,
253
+ "length_penalty": 1.0,
254
+ "max_length": 20,
255
+ "min_length": 0,
256
+ "model_type": "intern_vit_6b",
257
+ "no_repeat_ngram_size": 0,
258
+ "norm_type": "layer_norm",
259
+ "num_attention_heads": 16,
260
+ "num_beam_groups": 1,
261
+ "num_beams": 1,
262
+ "num_channels": 3,
263
+ "num_hidden_layers": 24,
264
+ "num_return_sequences": 1,
265
+ "output_attentions": false,
266
+ "output_hidden_states": false,
267
+ "output_scores": false,
268
+ "pad_token_id": null,
269
+ "patch_size": 14,
270
+ "prefix": null,
271
+ "problem_type": null,
272
+ "pruned_heads": {},
273
+ "qk_normalization": false,
274
+ "qkv_bias": true,
275
+ "remove_invalid_values": false,
276
+ "repetition_penalty": 1.0,
277
+ "return_dict": true,
278
+ "return_dict_in_generate": false,
279
+ "sep_token_id": null,
280
+ "suppress_tokens": null,
281
+ "task_specific_params": null,
282
+ "temperature": 1.0,
283
+ "tf_legacy_loss": false,
284
+ "tie_encoder_decoder": false,
285
+ "tie_word_embeddings": true,
286
+ "tokenizer_class": null,
287
+ "top_k": 50,
288
+ "top_p": 1.0,
289
+ "torch_dtype": "bfloat16",
290
+ "torchscript": false,
291
+ "transformers_version": "4.41.2",
292
+ "typical_p": 1.0,
293
+ "use_bfloat16": true,
294
+ "use_flash_attn": true
295
+ }
296
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.41.2"
4
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb91b5930fc035077a9f92b980cdc011200827d8f7918b666a086808228b055b
3
+ size 8293914834
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": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": true,
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<img>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "</img>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<IMG_CONTEXT>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "<quad>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "</quad>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "<ref>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "32017": {
167
+ "content": "</ref>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "32018": {
175
+ "content": "<box>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "32019": {
183
+ "content": "</box>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ }
190
+ },
191
+ "additional_special_tokens": [
192
+ "<img>",
193
+ "</img>",
194
+ "<IMG_CONTEXT>",
195
+ "<quad>",
196
+ "</quad>",
197
+ "<ref>",
198
+ "</ref>",
199
+ "<box>",
200
+ "</box>"
201
+ ],
202
+ "bos_token": "<s>",
203
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
204
+ "clean_up_tokenization_spaces": false,
205
+ "eos_token": "</s>",
206
+ "legacy": false,
207
+ "model_max_length": 8192,
208
+ "pad_token": "</s>",
209
+ "padding_side": "left",
210
+ "sp_model_kwargs": {},
211
+ "spaces_between_special_tokens": false,
212
+ "tokenizer_class": "LlamaTokenizer",
213
+ "unk_token": "<unk>",
214
+ "use_default_system_prompt": false
215
+ }