Hugging Face's logo

HuggingFaceM4
/
idefics-9b-instruct

Text Generation
Transformers
PyTorch
Safetensors
English
idefics
pretraining
multimodal
text
image
image-to-text
text-generation-inference
10 papers
Model card Files Community
16
VictorSanh HF staff commited on
Commit
5f31d1d
•
1 Parent(s): 5729d26

First commit

Browse files
Files changed (9) hide show
  1. added_tokens.json +4 -0
  2. config.json +47 -0
  3. generation_config.json +7 -0
  4. pytorch_model-00001-of-00002.bin +3 -0
  5. pytorch_model-00002-of-00002.bin +3 -0
  6. pytorch_model.bin.index.json +0 -0
  7. special_tokens_map.json +40 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +34 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<fake_token_around_image>": 32000,
3
+ "<image>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "None",
3
+ "additional_vocab_size": 2,
4
+ "alpha_initializer": "zeros",
5
+ "alpha_type": "float",
6
+ "alphas_initializer_range": 0.0,
7
+ "architectures": [
8
+ "VLlamaForCausalLM"
9
+ ],
10
+ "bos_token_id": 1,
11
+ "cross_layer_activation_function": "swiglu",
12
+ "cross_layer_interval": 4,
13
+ "dropout": 0.0,
14
+ "eos_token_id": 2,
15
+ "freeze_lm_head": false,
16
+ "freeze_text_layers": false,
17
+ "freeze_text_module_exceptions": [],
18
+ "freeze_vision_layers": false,
19
+ "freeze_vision_module_exceptions": [],
20
+ "hidden_act": "silu",
21
+ "hidden_size": 4096,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 11008,
24
+ "max_position_embeddings": 2048,
25
+ "max_sequence_length": 2048,
26
+ "model_type": "vllama",
27
+ "num_attention_heads": 32,
28
+ "num_hidden_layers": 32,
29
+ "pad_token_id": 0,
30
+ "qk_layer_norms": true,
31
+ "qk_layer_norms_perceiver": true,
32
+ "resampler_depth": 6,
33
+ "resampler_head_dim": 96,
34
+ "resampler_n_heads": 16,
35
+ "resampler_n_latents": 64,
36
+ "rms_norm_eps": 1e-06,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.28.0.dev0",
40
+ "use_cache": true,
41
+ "use_resampler": true,
42
+ "vision_embed_dim": 1280,
43
+ "vision_image_size": 224,
44
+ "vision_model_name": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
45
+ "vision_model_params": "{\"id2label\":{}, \"label2id\":{}}",
46
+ "vocab_size": 32000
47
+ }
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": "4.28.0.dev0"
7
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa56e10990afb6b882003571f094c95e37fae5471c4d8a318c7368644261ecb5
3
+ size 9971911147
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de33759f4bbb32b1c56bd7d891ab0966380e55d6a830afc87cc136a8e60513b
3
+ size 7887831155
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<fake_token_around_image>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<image>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": true,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "<unk>",
33
+ "unk_token": {
34
+ "content": "<unk>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
+ "special_tokens_map_file": "/Users/leotronchon/.cache/huggingface/hub/models--huggyllama--llama-7b/snapshots/8416d3fefb0cb3ff5775a7b13c1692d10ff1aa16/special_tokens_map.json",
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }