Hugging Face's logo

lamm-mit
/
Cephalo-Idefics2-vision-3x8b-beta

Image-Text-to-Text
Transformers
Safetensors
multilingual
English
idefics2_moe
text-generation
nlp
code
vision
chemistry
engineering
biology
bio-inspired
text-generation-inference
materials science
mixture-of-experts
science
latex
conversational
custom_code
Model card Files Community
mjbuehler commited on
Commit
6241b4b
•
1 Parent(s): be3fb98

Upload Idefics2ForCausalLMMoE

Browse files
Files changed (12) hide show
  1. config.json +240 -0
  2. generation_config.json +7 -0
  3. model-00001-of-00009.safetensors +3 -0
  4. model-00002-of-00009.safetensors +3 -0
  5. model-00003-of-00009.safetensors +3 -0
  6. model-00004-of-00009.safetensors +3 -0
  7. model-00005-of-00009.safetensors +3 -0
  8. model-00006-of-00009.safetensors +3 -0
  9. model-00007-of-00009.safetensors +3 -0
  10. model-00008-of-00009.safetensors +3 -0
  11. model-00009-of-00009.safetensors +3 -0
  12. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
3
+ "architectures": [
4
+ "Idefics2ForCausalLMMoE"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "moe_idefics2.Idefics2ForCausalLMMoEConfig",
8
+ "AutoModelForCausalLM": "moe_idefics2.Idefics2ForCausalLMMoE"
9
+ },
10
+ "image_token_id": 32001,
11
+ "k": 1,
12
+ "model_type": "idefics2_moe",
13
+ "num_expert_models": 3,
14
+ "perceiver_config": {
15
+ "_name_or_path": "",
16
+ "add_cross_attention": false,
17
+ "architectures": null,
18
+ "attention_dropout": 0.0,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": null,
22
+ "chunk_size_feed_forward": 0,
23
+ "cross_attention_hidden_size": null,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": null,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "hidden_act": "silu",
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "is_decoder": false,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "min_length": 0,
48
+ "model_type": "idefics2",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_key_value_heads": 4,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "resampler_depth": 3,
64
+ "resampler_head_dim": 96,
65
+ "resampler_n_heads": 16,
66
+ "resampler_n_latents": 64,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "typical_p": 1.0,
82
+ "use_bfloat16": false
83
+ },
84
+ "text_config": {
85
+ "_name_or_path": "",
86
+ "add_cross_attention": false,
87
+ "architectures": null,
88
+ "attention_dropout": 0.0,
89
+ "bad_words_ids": null,
90
+ "begin_suppress_tokens": null,
91
+ "bos_token_id": 1,
92
+ "chunk_size_feed_forward": 0,
93
+ "cross_attention_hidden_size": null,
94
+ "decoder_start_token_id": null,
95
+ "diversity_penalty": 0.0,
96
+ "do_sample": false,
97
+ "early_stopping": false,
98
+ "encoder_no_repeat_ngram_size": 0,
99
+ "eos_token_id": 2,
100
+ "exponential_decay_length_penalty": null,
101
+ "finetuning_task": null,
102
+ "forced_bos_token_id": null,
103
+ "forced_eos_token_id": null,
104
+ "hidden_act": "silu",
105
+ "hidden_size": 4096,
106
+ "id2label": {
107
+ "0": "LABEL_0",
108
+ "1": "LABEL_1"
109
+ },
110
+ "initializer_range": 0.02,
111
+ "intermediate_size": 14336,
112
+ "is_decoder": false,
113
+ "is_encoder_decoder": false,
114
+ "label2id": {
115
+ "LABEL_0": 0,
116
+ "LABEL_1": 1
117
+ },
118
+ "length_penalty": 1.0,
119
+ "max_length": 20,
120
+ "max_position_embeddings": 32768,
121
+ "min_length": 0,
122
+ "model_type": "mistral",
123
+ "no_repeat_ngram_size": 0,
124
+ "num_attention_heads": 32,
125
+ "num_beam_groups": 1,
126
+ "num_beams": 1,
127
+ "num_hidden_layers": 32,
128
+ "num_key_value_heads": 8,
129
+ "num_return_sequences": 1,
130
+ "output_attentions": false,
131
+ "output_hidden_states": false,
132
+ "output_scores": false,
133
+ "pad_token_id": 0,
134
+ "prefix": null,
135
+ "problem_type": null,
136
+ "pruned_heads": {},
137
+ "remove_invalid_values": false,
138
+ "repetition_penalty": 1.0,
139
+ "return_dict": true,
140
+ "return_dict_in_generate": false,
141
+ "rms_norm_eps": 1e-05,
142
+ "rope_theta": 10000.0,
143
+ "sep_token_id": null,
144
+ "sliding_window": 4096,
145
+ "suppress_tokens": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tf_legacy_loss": false,
149
+ "tie_encoder_decoder": false,
150
+ "tie_word_embeddings": false,
151
+ "tokenizer_class": null,
152
+ "top_k": 50,
153
+ "top_p": 1.0,
154
+ "torch_dtype": null,
155
+ "torchscript": false,
156
+ "typical_p": 1.0,
157
+ "use_bfloat16": false,
158
+ "use_cache": true,
159
+ "vocab_size": 32003
160
+ },
161
+ "tie_word_embeddings": false,
162
+ "torch_dtype": "bfloat16",
163
+ "transformers_version": "4.41.2",
164
+ "use_cache": true,
165
+ "use_embeddings_in_router": false,
166
+ "vision_config": {
167
+ "_name_or_path": "",
168
+ "add_cross_attention": false,
169
+ "architectures": null,
170
+ "attention_dropout": 0.0,
171
+ "bad_words_ids": null,
172
+ "begin_suppress_tokens": null,
173
+ "bos_token_id": null,
174
+ "chunk_size_feed_forward": 0,
175
+ "cross_attention_hidden_size": null,
176
+ "decoder_start_token_id": null,
177
+ "diversity_penalty": 0.0,
178
+ "do_sample": false,
179
+ "early_stopping": false,
180
+ "encoder_no_repeat_ngram_size": 0,
181
+ "eos_token_id": null,
182
+ "exponential_decay_length_penalty": null,
183
+ "finetuning_task": null,
184
+ "forced_bos_token_id": null,
185
+ "forced_eos_token_id": null,
186
+ "hidden_act": "gelu_pytorch_tanh",
187
+ "hidden_size": 1152,
188
+ "id2label": {
189
+ "0": "LABEL_0",
190
+ "1": "LABEL_1"
191
+ },
192
+ "image_size": 980,
193
+ "initializer_range": 0.02,
194
+ "intermediate_size": 4304,
195
+ "is_decoder": false,
196
+ "is_encoder_decoder": false,
197
+ "label2id": {
198
+ "LABEL_0": 0,
199
+ "LABEL_1": 1
200
+ },
201
+ "layer_norm_eps": 1e-06,
202
+ "length_penalty": 1.0,
203
+ "max_length": 20,
204
+ "min_length": 0,
205
+ "model_type": "idefics2",
206
+ "no_repeat_ngram_size": 0,
207
+ "num_attention_heads": 16,
208
+ "num_beam_groups": 1,
209
+ "num_beams": 1,
210
+ "num_channels": 3,
211
+ "num_hidden_layers": 27,
212
+ "num_return_sequences": 1,
213
+ "output_attentions": false,
214
+ "output_hidden_states": false,
215
+ "output_scores": false,
216
+ "pad_token_id": null,
217
+ "patch_size": 14,
218
+ "prefix": null,
219
+ "problem_type": null,
220
+ "pruned_heads": {},
221
+ "remove_invalid_values": false,
222
+ "repetition_penalty": 1.0,
223
+ "return_dict": true,
224
+ "return_dict_in_generate": false,
225
+ "sep_token_id": null,
226
+ "suppress_tokens": null,
227
+ "task_specific_params": null,
228
+ "temperature": 1.0,
229
+ "tf_legacy_loss": false,
230
+ "tie_encoder_decoder": false,
231
+ "tie_word_embeddings": true,
232
+ "tokenizer_class": null,
233
+ "top_k": 50,
234
+ "top_p": 1.0,
235
+ "torch_dtype": null,
236
+ "torchscript": false,
237
+ "typical_p": 1.0,
238
+ "use_bfloat16": false
239
+ }
240
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.2"
7
+ }
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9636d5a4a6023653d3597fbf811ab6d5be3c5d5a5a39dde8b195a20eb34ce8b
3
+ size 4949931332
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53acf585f2364433addfdfc1ea13556816b7f779b906a5e61c665d435913a20f
3
+ size 4915897936
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4072421f6aee6f5d5e1582e3218f5098b6c89a783c4b5a7579a1f10160428228
3
+ size 4915897952
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0e39ba08baa4555fd9f13395377b09a7f655b0cace7bde718e05e3a20433e5
3
+ size 4999826118
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4830d3306e458c85e09c237758502aedb4846d3a871d17ae7e1b791f6d4a8b9
3
+ size 4915898008
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723934d102c574d78ab88a4eebcbc094b5c20e7305dd73af82a2b4d7af635873
3
+ size 4915898000
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33dd4750b77351a530c161a8ddec4195d5468a5d4a10bfc675b657ee5e54d50
3
+ size 4999826118
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a06dec41f64221e2b1118c0b0ff0d25e3de03d5a2be39766d207c84edc2ad155
3
+ size 4741866408
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2fccd6d7bce2f96751378139aa82609cab5f55395108dd28fdf636220218f3
3
+ size 524337280
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff