Hugging Face's logo

HuggingFaceM4
/
idefics-9b

Text Generation
Transformers
PyTorch
Safetensors
4 datasets
English
idefics
pretraining
multimodal
text
image
image-to-text
text-generation-inference
10 papers
Model card Files Community
15
stas commited on
Commit
b07ebf3
•
1 Parent(s): 463033a

re-shard to 2GB

Browse files
Files changed (42) hide show
  1. config.json +145 -13
  2. generation_config.json +1 -1
  3. model-00001-of-00002.safetensors → model-00001-of-00019.safetensors +2 -2
  4. model-00002-of-00002.safetensors → model-00002-of-00019.safetensors +2 -2
  5. pytorch_model-00001-of-00002.bin → model-00003-of-00019.safetensors +2 -2
  6. pytorch_model-00002-of-00002.bin → model-00004-of-00019.safetensors +2 -2
  7. model-00005-of-00019.safetensors +3 -0
  8. model-00006-of-00019.safetensors +3 -0
  9. model-00007-of-00019.safetensors +3 -0
  10. model-00008-of-00019.safetensors +3 -0
  11. model-00009-of-00019.safetensors +3 -0
  12. model-00010-of-00019.safetensors +3 -0
  13. model-00011-of-00019.safetensors +3 -0
  14. model-00012-of-00019.safetensors +3 -0
  15. model-00013-of-00019.safetensors +3 -0
  16. model-00014-of-00019.safetensors +3 -0
  17. model-00015-of-00019.safetensors +3 -0
  18. model-00016-of-00019.safetensors +3 -0
  19. model-00017-of-00019.safetensors +3 -0
  20. model-00018-of-00019.safetensors +3 -0
  21. model-00019-of-00019.safetensors +3 -0
  22. model.safetensors.index.json +0 -0
  23. pytorch_model-00001-of-00019.bin +3 -0
  24. pytorch_model-00002-of-00019.bin +3 -0
  25. pytorch_model-00003-of-00019.bin +3 -0
  26. pytorch_model-00004-of-00019.bin +3 -0
  27. pytorch_model-00005-of-00019.bin +3 -0
  28. pytorch_model-00006-of-00019.bin +3 -0
  29. pytorch_model-00007-of-00019.bin +3 -0
  30. pytorch_model-00008-of-00019.bin +3 -0
  31. pytorch_model-00009-of-00019.bin +3 -0
  32. pytorch_model-00010-of-00019.bin +3 -0
  33. pytorch_model-00011-of-00019.bin +3 -0
  34. pytorch_model-00012-of-00019.bin +3 -0
  35. pytorch_model-00013-of-00019.bin +3 -0
  36. pytorch_model-00014-of-00019.bin +3 -0
  37. pytorch_model-00015-of-00019.bin +3 -0
  38. pytorch_model-00016-of-00019.bin +3 -0
  39. pytorch_model-00017-of-00019.bin +3 -0
  40. pytorch_model-00018-of-00019.bin +3 -0
  41. pytorch_model-00019-of-00019.bin +3 -0
  42. pytorch_model.bin.index.json +0 -0
config.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
- "_name_or_path": "None",
 
3
  "additional_vocab_size": 2,
4
  "alpha_initializer": "zeros",
5
  "alpha_type": "float",
@@ -27,27 +28,158 @@
27
  "num_attention_heads": 32,
28
  "num_hidden_layers": 32,
29
  "pad_token_id": 0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "qk_layer_norms": true,
31
  "rms_norm_eps": 1e-06,
32
  "tie_word_embeddings": false,
33
- "torch_dtype": "bfloat16",
34
  "transformers_version": "4.28.0.dev0",
35
  "use_cache": true,
36
  "use_resampler": true,
37
- "vocab_size": 32000,
38
  "vision_config": {
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  "embed_dim": 1280,
 
 
 
 
 
 
 
 
 
 
 
40
  "image_size": 224,
 
 
41
  "intermediate_size": 5120,
42
- "patch_size": 14,
 
 
 
 
 
 
 
 
 
 
 
43
  "num_attention_heads": 16,
44
- "num_hidden_layers": 32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  },
46
- "perceiver_config": {
47
- "qk_layer_norms_perceiver": true,
48
- "resampler_depth": 6,
49
- "resampler_head_dim": 96,
50
- "resampler_n_heads": 16,
51
- "resampler_n_latents": 64
52
- }
53
- }
 
1
  {
2
+ "_commit_hash": null,
3
+ "_name_or_path": ".",
4
  "additional_vocab_size": 2,
5
  "alpha_initializer": "zeros",
6
  "alpha_type": "float",
 
28
  "num_attention_heads": 32,
29
  "num_hidden_layers": 32,
30
  "pad_token_id": 0,
31
+ "perceiver_config": {
32
+ "_name_or_path": "",
33
+ "add_cross_attention": false,
34
+ "architectures": null,
35
+ "bad_words_ids": null,
36
+ "begin_suppress_tokens": null,
37
+ "bos_token_id": null,
38
+ "chunk_size_feed_forward": 0,
39
+ "cross_attention_hidden_size": null,
40
+ "decoder_start_token_id": null,
41
+ "diversity_penalty": 0.0,
42
+ "do_sample": false,
43
+ "early_stopping": false,
44
+ "encoder_no_repeat_ngram_size": 0,
45
+ "eos_token_id": null,
46
+ "exponential_decay_length_penalty": null,
47
+ "finetuning_task": null,
48
+ "forced_bos_token_id": null,
49
+ "forced_eos_token_id": null,
50
+ "id2label": {
51
+ "0": "LABEL_0",
52
+ "1": "LABEL_1"
53
+ },
54
+ "is_decoder": false,
55
+ "is_encoder_decoder": false,
56
+ "label2id": {
57
+ "LABEL_0": 0,
58
+ "LABEL_1": 1
59
+ },
60
+ "length_penalty": 1.0,
61
+ "max_length": 20,
62
+ "min_length": 0,
63
+ "model_type": "idefics",
64
+ "no_repeat_ngram_size": 0,
65
+ "num_beam_groups": 1,
66
+ "num_beams": 1,
67
+ "num_return_sequences": 1,
68
+ "output_attentions": false,
69
+ "output_hidden_states": false,
70
+ "output_scores": false,
71
+ "pad_token_id": null,
72
+ "prefix": null,
73
+ "problem_type": null,
74
+ "pruned_heads": {},
75
+ "qk_layer_norms_perceiver": true,
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "resampler_depth": 6,
79
+ "resampler_head_dim": 96,
80
+ "resampler_n_heads": 16,
81
+ "resampler_n_latents": 64,
82
+ "return_dict": true,
83
+ "return_dict_in_generate": false,
84
+ "sep_token_id": null,
85
+ "suppress_tokens": null,
86
+ "task_specific_params": null,
87
+ "temperature": 1.0,
88
+ "tf_legacy_loss": false,
89
+ "tie_encoder_decoder": false,
90
+ "tie_word_embeddings": true,
91
+ "tokenizer_class": null,
92
+ "top_k": 50,
93
+ "top_p": 1.0,
94
+ "torch_dtype": null,
95
+ "torchscript": false,
96
+ "transformers_version": "4.32.0.dev0",
97
+ "typical_p": 1.0,
98
+ "use_bfloat16": false,
99
+ "use_resampler": false
100
+ },
101
  "qk_layer_norms": true,
102
  "rms_norm_eps": 1e-06,
103
  "tie_word_embeddings": false,
104
+ "torch_dtype": "float32",
105
  "transformers_version": "4.28.0.dev0",
106
  "use_cache": true,
107
  "use_resampler": true,
 
108
  "vision_config": {
109
+ "_name_or_path": "",
110
+ "add_cross_attention": false,
111
+ "architectures": null,
112
+ "attention_dropout": 0.0,
113
+ "bad_words_ids": null,
114
+ "begin_suppress_tokens": null,
115
+ "bos_token_id": null,
116
+ "chunk_size_feed_forward": 0,
117
+ "cross_attention_hidden_size": null,
118
+ "decoder_start_token_id": null,
119
+ "diversity_penalty": 0.0,
120
+ "do_sample": false,
121
+ "early_stopping": false,
122
  "embed_dim": 1280,
123
+ "encoder_no_repeat_ngram_size": 0,
124
+ "eos_token_id": null,
125
+ "exponential_decay_length_penalty": null,
126
+ "finetuning_task": null,
127
+ "forced_bos_token_id": null,
128
+ "forced_eos_token_id": null,
129
+ "hidden_act": "quick_gelu",
130
+ "id2label": {
131
+ "0": "LABEL_0",
132
+ "1": "LABEL_1"
133
+ },
134
  "image_size": 224,
135
+ "initializer_factor": 1.0,
136
+ "initializer_range": 0.02,
137
  "intermediate_size": 5120,
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-05,
145
+ "length_penalty": 1.0,
146
+ "max_length": 20,
147
+ "min_length": 0,
148
+ "model_type": "idefics",
149
+ "no_repeat_ngram_size": 0,
150
  "num_attention_heads": 16,
151
+ "num_beam_groups": 1,
152
+ "num_beams": 1,
153
+ "num_channels": 3,
154
+ "num_hidden_layers": 32,
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
+ "remove_invalid_values": false,
165
+ "repetition_penalty": 1.0,
166
+ "return_dict": true,
167
+ "return_dict_in_generate": false,
168
+ "sep_token_id": null,
169
+ "suppress_tokens": null,
170
+ "task_specific_params": null,
171
+ "temperature": 1.0,
172
+ "tf_legacy_loss": false,
173
+ "tie_encoder_decoder": false,
174
+ "tie_word_embeddings": true,
175
+ "tokenizer_class": null,
176
+ "top_k": 50,
177
+ "top_p": 1.0,
178
+ "torch_dtype": null,
179
+ "torchscript": false,
180
+ "transformers_version": "4.32.0.dev0",
181
+ "typical_p": 1.0,
182
+ "use_bfloat16": false
183
  },
184
+ "vocab_size": 32000
185
+ }
 
 
 
 
 
 
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.28.0.dev0"
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.32.0.dev0"
7
  }
model-00001-of-00002.safetensors → model-00001-of-00019.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:011a49d41e8607ccb5f650dad9051c166d52478710b1ed8c9fd74259237fa998
3
- size 9971725832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd17b50b8b9d02d2a410fbd5b84124f4d20aceb597bbb45d114310d3005c2fd
3
+ size 1997957904
model-00002-of-00002.safetensors → model-00002-of-00019.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19088005fc5e28d166537553fb49ff9e2208847dba4c8a724879c0eb9680f8a3
3
- size 7887778512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c73e9247c87d87526f0a53eb7537f51e58b2afbf8459c5e22fa905336ddbdc
3
+ size 1821791352
pytorch_model-00001-of-00002.bin → model-00003-of-00019.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c20e9225c6cce75d43b3955e929cc6b8b31174bb0a133b1396225da75227667e
3
- size 9971911147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:109eb6a68b00bfb430c45dfb00bf1fa0d59653e371bcaabc7e4cfdf8840678cc
3
+ size 1979780072
pytorch_model-00002-of-00002.bin → model-00004-of-00019.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8d3234e836ab51aa50279de8db240763f4bf274eb25ac90887e72f7b111cae7
3
- size 7887831155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf6542348cd7da50cfa9746d1c3e000dbde569f4bfef2b9d91e6d5238082993
3
+ size 1933675824
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af265a831028c2dc5ec042c27b06c833f38352564a1c94f7483bdec236f6514
3
+ size 1933643208
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed08f44bc877e38d52bcb51ce512d55ea9698ced30eb67d07e30b216b4e8797d
3
+ size 1979813064
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5054c16adef2fb309140d2cccca228bac9e72bd3ea46e0149e259966f2f65c68
3
+ size 1887506008
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18291f1ed538407d0d0ebbc4b2e1c4ea5d76b54fc76267bac2059cf3c353eff1
3
+ size 1979780096
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52acf17b847eea2c3ca8067badd2061bbd26a424a9764820316c3c55b9efc6bd
3
+ size 1933675856
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:462c8a90066bb5cd9d88a75d5292accf6a4e951008378395b63fdd6c9ca5e24e
3
+ size 1933643232
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1737bedead11b03e731e0a9a56224cde806d8602af52dc3e90ffe6fe3cd38e08
3
+ size 1979813088
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7fd23d6383eb24855b31a24c88fc26469429feb8db883b88fec7f432d1d18ea
3
+ size 1887506008
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e73f319498b476ee615742d1b6301f9944ca4c44c9bbe0183145db771fbfbfa
3
+ size 1979780096
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23440d85fc6e2d84fc1505614314d1a1a31d4ce7163810376e15135c8d2f12eb
3
+ size 1933675856
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68cc998a89cd4c4166b2b9b44f0cb99e1ec39fd8ee5c8b5814d886b2a9acfdc6
3
+ size 1933643232
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1acf64f64b8b5a537d0b3193cabfdd8d8d5d54341c0d74ea88e3001dd45a7fb
3
+ size 1971430256
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6958fb49015243e0050250dfed01183ec0ee8b32c844683cf1416d8fb8265da1
3
+ size 1975622592
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd1cb35844cd3cb3379cf21bec2c23a6be3eecd0e69f2fa8d28634d9ca24990
3
+ size 1971397088
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e1083c51108aa7b68e25dbf62915195a1a8a23911496971f4fb44aa03bb146
3
+ size 704725688
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990ffc571b5c73fd49e55e4c723e09ca7693b4348fef71725c2c4a017fbd1ce0
3
+ size 1998026228
pytorch_model-00002-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8e081395dba31d2e2695ff62a57bd8153900bedee690adbe5dbc4c9ed0fe1b0
3
+ size 1821862213
pytorch_model-00003-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6b46a9f64cb269fe8b54077f42a1fcd1e159f6e8160ca77a16d9962aedb1d9
3
+ size 1979785051
pytorch_model-00004-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d525b3ad30b9697ed02c9f07f2e0e301f83ae1005c6ab39862be33a9aed7004f
3
+ size 1933681361
pytorch_model-00005-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a71594bd7217f21230cd13efa94d8f6a752a71b2950b17f1d674c2f52fd3716
3
+ size 1933648575
pytorch_model-00006-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d5a20c4c046e02520d1563fb4d33301530770bcd2c5de167d3074aa58498ae
3
+ size 1979818431
pytorch_model-00007-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea98e1b751f214a5a76cb212859667cdde5b965d162d718a9093cc5411ccf2c
3
+ size 1887511569
pytorch_model-00008-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05608b713472d92b23770c6065fc0ccd79799c19e61dd737bf7bc42b3ed9859a
3
+ size 1979785051
pytorch_model-00009-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d49b3957db8bda9dbd9f00458b9f8c8448fa7949b7b4d51c7dddde14eb1fc81
3
+ size 1933681425
pytorch_model-00010-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039d41e5bd9b7aa4f58ccd3706521b6341a508cda69813e58aebd80a0359c90f
3
+ size 1933648575
pytorch_model-00011-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c55837eca093bc6107a9aa611c76ecc4da8a83601fbac1ee0f5dda578007b5
3
+ size 1979818431
pytorch_model-00012-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba54ec2ebb0d428bdb10fed2e41894f8a2149c1334a3ddbdbc368a06f37f74d
3
+ size 1887511569
pytorch_model-00013-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2538788612c23b63b8f92892dd200f362a1f3d990d262724101e62485b4b26
3
+ size 1979785051
pytorch_model-00014-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f542772157427e780b65c445ad5841ed613693a0f0efd61ff9aabfd78d51da5e
3
+ size 1933681425
pytorch_model-00015-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c2037e5e4131a0f4bb1056de451a56a08e199971c2be011b349c314b79ccff
3
+ size 1933648575
pytorch_model-00016-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdd0da29f21b4166f1dc1d4333146b6ee726126409e4d39bcaa0dcffc31e7d91
3
+ size 1971439217
pytorch_model-00017-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8486fbd00b2d946d824b9b1198353790a0fb1173e54ae5aa44b924141fd4a42
3
+ size 1975630213
pytorch_model-00018-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e51d6c05db1e5c1ce6307ece65eb5b24abf6997ff428531e55d71f377bb2646
3
+ size 1971405161
pytorch_model-00019-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9670df10ee765050421f30fda997e3c269e35437724eb2cec731573ab0935117
3
+ size 704727487
pytorch_model.bin.index.json CHANGED
The diff for this file is too large to render. See raw diff