Hugging Face's logo

BK-Lee
/
Phantom-3.8B

Safetensors
phantom
Model card Files Community
BK-Lee commited on
Commit
7349a53
•
1 Parent(s): 1f7d63f

Upload 10 files

Browse files
Files changed (10) hide show
  1. added_tokens.json +22 -0
  2. config.json +298 -0
  3. generation_config.json +4 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +0 -0
  7. special_tokens_map.json +41 -0
  8. tokenizer.json +0 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +214 -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 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/mnt/ssd/lbk-cvpr/checkpoints/models--microsoft--Phi-3-mini-128k-instruct",
4
+ "architectures": [
5
+ "PhantomForCausalLM"
6
+ ],
7
+ "downsample_ratio": 0.5,
8
+ "dynamic_image_size": true,
9
+ "eos_token_id": 32007,
10
+ "force_image_size": 448,
11
+ "ignore_index": -100,
12
+ "image_token_index": 32013,
13
+ "llm_config": {
14
+ "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
15
+ "add_cross_attention": false,
16
+ "architectures": [
17
+ "Phi3ForCausalLM"
18
+ ],
19
+ "attention_dropout": 0.0,
20
+ "auto_map": {
21
+ "AutoConfig": "configuration_phi3.Phi3Config",
22
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
23
+ },
24
+ "bad_words_ids": null,
25
+ "begin_suppress_tokens": null,
26
+ "bos_token_id": 1,
27
+ "chunk_size_feed_forward": 0,
28
+ "cross_attention_hidden_size": null,
29
+ "decoder_start_token_id": null,
30
+ "diversity_penalty": 0.0,
31
+ "do_sample": false,
32
+ "early_stopping": false,
33
+ "embd_pdrop": 0.0,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 32000,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": null,
40
+ "hidden_act": "silu",
41
+ "hidden_size": 3072,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1"
45
+ },
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 8192,
48
+ "is_decoder": false,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_position_embeddings": 131072,
57
+ "min_length": 0,
58
+ "model_type": "phi3",
59
+ "no_repeat_ngram_size": 0,
60
+ "num_attention_heads": 32,
61
+ "num_beam_groups": 1,
62
+ "num_beams": 1,
63
+ "num_hidden_layers": 32,
64
+ "num_key_value_heads": 32,
65
+ "num_return_sequences": 1,
66
+ "original_max_position_embeddings": 4096,
67
+ "output_attentions": false,
68
+ "output_hidden_states": false,
69
+ "output_scores": false,
70
+ "pad_token_id": 32000,
71
+ "prefix": null,
72
+ "problem_type": null,
73
+ "pruned_heads": {},
74
+ "remove_invalid_values": false,
75
+ "repetition_penalty": 1.0,
76
+ "resid_pdrop": 0.0,
77
+ "return_dict": true,
78
+ "return_dict_in_generate": false,
79
+ "rms_norm_eps": 1e-05,
80
+ "rope_scaling": {
81
+ "long_factor": [
82
+ 1.0299999713897705,
83
+ 1.0499999523162842,
84
+ 1.0499999523162842,
85
+ 1.0799999237060547,
86
+ 1.2299998998641968,
87
+ 1.2299998998641968,
88
+ 1.2999999523162842,
89
+ 1.4499999284744263,
90
+ 1.5999999046325684,
91
+ 1.6499998569488525,
92
+ 1.8999998569488525,
93
+ 2.859999895095825,
94
+ 3.68999981880188,
95
+ 5.419999599456787,
96
+ 5.489999771118164,
97
+ 5.489999771118164,
98
+ 9.09000015258789,
99
+ 11.579999923706055,
100
+ 15.65999984741211,
101
+ 15.769999504089355,
102
+ 15.789999961853027,
103
+ 18.360000610351562,
104
+ 21.989999771118164,
105
+ 23.079999923706055,
106
+ 30.009998321533203,
107
+ 32.35000228881836,
108
+ 32.590003967285156,
109
+ 35.56000518798828,
110
+ 39.95000457763672,
111
+ 53.840003967285156,
112
+ 56.20000457763672,
113
+ 57.95000457763672,
114
+ 59.29000473022461,
115
+ 59.77000427246094,
116
+ 59.920005798339844,
117
+ 61.190006256103516,
118
+ 61.96000671386719,
119
+ 62.50000762939453,
120
+ 63.3700065612793,
121
+ 63.48000717163086,
122
+ 63.48000717163086,
123
+ 63.66000747680664,
124
+ 63.850006103515625,
125
+ 64.08000946044922,
126
+ 64.760009765625,
127
+ 64.80001068115234,
128
+ 64.81001281738281,
129
+ 64.81001281738281
130
+ ],
131
+ "short_factor": [
132
+ 1.05,
133
+ 1.05,
134
+ 1.05,
135
+ 1.1,
136
+ 1.1,
137
+ 1.1500000000000001,
138
+ 1.2000000000000002,
139
+ 1.2500000000000002,
140
+ 1.3000000000000003,
141
+ 1.3500000000000003,
142
+ 1.5000000000000004,
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
+ 2.000000000000001,
161
+ 2.000000000000001,
162
+ 2.000000000000001,
163
+ 2.000000000000001,
164
+ 2.0500000000000007,
165
+ 2.0500000000000007,
166
+ 2.0500000000000007,
167
+ 2.1000000000000005,
168
+ 2.1000000000000005,
169
+ 2.1000000000000005,
170
+ 2.1500000000000004,
171
+ 2.1500000000000004,
172
+ 2.3499999999999996,
173
+ 2.549999999999999,
174
+ 2.5999999999999988,
175
+ 2.5999999999999988,
176
+ 2.7499999999999982,
177
+ 2.849999999999998,
178
+ 2.849999999999998,
179
+ 2.9499999999999975
180
+ ],
181
+ "type": "su"
182
+ },
183
+ "rope_theta": 10000.0,
184
+ "sep_token_id": null,
185
+ "sliding_window": 262144,
186
+ "suppress_tokens": null,
187
+ "task_specific_params": null,
188
+ "temperature": 1.0,
189
+ "tf_legacy_loss": false,
190
+ "tie_encoder_decoder": false,
191
+ "tie_word_embeddings": false,
192
+ "tokenizer_class": null,
193
+ "top_k": 50,
194
+ "top_p": 1.0,
195
+ "torch_dtype": "bfloat16",
196
+ "torchscript": false,
197
+ "transformers_version": "4.37.2",
198
+ "typical_p": 1.0,
199
+ "use_bfloat16": true,
200
+ "use_cache": false,
201
+ "vocab_size": 32020
202
+ },
203
+ "max_dynamic_patch": 12,
204
+ "min_dynamic_patch": 1,
205
+ "model_type": "phantom",
206
+ "pad_token_id": 32007,
207
+ "select_layer": -1,
208
+ "template": "phi3-chat",
209
+ "torch_dtype": "bfloat16",
210
+ "transformers_version": null,
211
+ "use_backbone_lora": 0,
212
+ "use_llm_lora": 0,
213
+ "use_thumbnail": true,
214
+ "vision_config": {
215
+ "_name_or_path": "",
216
+ "add_cross_attention": false,
217
+ "architectures": [
218
+ "InternVisionModel"
219
+ ],
220
+ "attention_dropout": 0.0,
221
+ "bad_words_ids": null,
222
+ "begin_suppress_tokens": null,
223
+ "bos_token_id": null,
224
+ "chunk_size_feed_forward": 0,
225
+ "cross_attention_hidden_size": null,
226
+ "decoder_start_token_id": null,
227
+ "diversity_penalty": 0.0,
228
+ "do_sample": false,
229
+ "drop_path_rate": 0.0,
230
+ "dropout": 0.0,
231
+ "early_stopping": false,
232
+ "encoder_no_repeat_ngram_size": 0,
233
+ "eos_token_id": null,
234
+ "exponential_decay_length_penalty": null,
235
+ "finetuning_task": null,
236
+ "forced_bos_token_id": null,
237
+ "forced_eos_token_id": null,
238
+ "hidden_act": "gelu",
239
+ "hidden_size": 1024,
240
+ "id2label": {
241
+ "0": "LABEL_0",
242
+ "1": "LABEL_1"
243
+ },
244
+ "image_size": 448,
245
+ "initializer_factor": 1.0,
246
+ "initializer_range": 0.02,
247
+ "intermediate_size": 4096,
248
+ "is_decoder": false,
249
+ "is_encoder_decoder": false,
250
+ "label2id": {
251
+ "LABEL_0": 0,
252
+ "LABEL_1": 1
253
+ },
254
+ "layer_norm_eps": 1e-06,
255
+ "length_penalty": 1.0,
256
+ "max_length": 20,
257
+ "min_length": 0,
258
+ "model_type": "intern_vit_300m",
259
+ "no_repeat_ngram_size": 0,
260
+ "norm_type": "layer_norm",
261
+ "num_attention_heads": 16,
262
+ "num_beam_groups": 1,
263
+ "num_beams": 1,
264
+ "num_channels": 3,
265
+ "num_hidden_layers": 24,
266
+ "num_return_sequences": 1,
267
+ "output_attentions": false,
268
+ "output_hidden_states": false,
269
+ "output_scores": false,
270
+ "pad_token_id": null,
271
+ "patch_size": 14,
272
+ "prefix": null,
273
+ "problem_type": null,
274
+ "pruned_heads": {},
275
+ "qk_normalization": false,
276
+ "qkv_bias": true,
277
+ "remove_invalid_values": false,
278
+ "repetition_penalty": 1.0,
279
+ "return_dict": true,
280
+ "return_dict_in_generate": false,
281
+ "sep_token_id": null,
282
+ "suppress_tokens": null,
283
+ "task_specific_params": null,
284
+ "temperature": 1.0,
285
+ "tf_legacy_loss": false,
286
+ "tie_encoder_decoder": false,
287
+ "tie_word_embeddings": true,
288
+ "tokenizer_class": null,
289
+ "top_k": 50,
290
+ "top_p": 1.0,
291
+ "torch_dtype": "bfloat16",
292
+ "torchscript": false,
293
+ "transformers_version": "4.37.2",
294
+ "typical_p": 1.0,
295
+ "use_bfloat16": true,
296
+ "use_flash_attn": true
297
+ }
298
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.37.2"
4
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4f7b69aca42078f67ba9f8d8520d01e6207a68632fdcde07f2eced4a943cd83
3
+ size 4961646364
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c297a396a84eab6626913bf21e8dc1557aee59c20832c06594a15a7631d2c9b5
3
+ size 3339296772
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": "<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 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<img>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "</img>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<IMG_CONTEXT>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<quad>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "</quad>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<ref>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "</ref>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<box>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "</box>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<img>",
192
+ "</img>",
193
+ "<IMG_CONTEXT>",
194
+ "<quad>",
195
+ "</quad>",
196
+ "<ref>",
197
+ "</ref>",
198
+ "<box>",
199
+ "</box>"
200
+ ],
201
+ "bos_token": "<s>",
202
+ "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 %}",
203
+ "clean_up_tokenization_spaces": false,
204
+ "eos_token": "</s>",
205
+ "legacy": false,
206
+ "model_max_length": 8192,
207
+ "pad_token": "</s>",
208
+ "padding_side": "left",
209
+ "sp_model_kwargs": {},
210
+ "spaces_between_special_tokens": false,
211
+ "tokenizer_class": "LlamaTokenizer",
212
+ "unk_token": "<unk>",
213
+ "use_default_system_prompt": false
214
+ }