Image-Text-to-Text
Transformers
Safetensors
English
idefics2
pretraining
multimodal
vision
quantized
4-bit precision
AWQ
Inference Endpoints
awq
VictorSanh HF staff commited on
Commit
91ef35c
1 Parent(s): 2ff01c8

final checkpoints - awq quantization

Browse files
README.md CHANGED
@@ -1,3 +1,32 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
1
  ---
2
  license: apache-2.0
3
+ datasets:
4
+ - HuggingFaceM4/OBELICS
5
+ - laion/laion-coco
6
+ - wikipedia
7
+ - facebook/pmd
8
+ - pixparse/idl-wds
9
+ - pixparse/pdfa-eng-wds
10
+ - wendlerc/RenderedText
11
+ - HuggingFaceM4/the_cauldron
12
+ - teknium/OpenHermes-2.5
13
+ - GAIR/lima
14
+ - databricks/databricks-dolly-15k
15
+ - meta-math/MetaMathQA
16
+ - TIGER-Lab/MathInstruct
17
+ - microsoft/orca-math-word-problems-200k
18
+ - camel-ai/math
19
+ - AtlasUnified/atlas-math-sets
20
+ - tiedong/goat
21
+ language:
22
+ - en
23
+ tags:
24
+ - multimodal
25
+ - vision
26
+ - image-text-to-text
27
+ - quantized
28
+ - 4-bit
29
+ - AWQ
30
  ---
31
+
32
+ 4-bit AWQ-quantized version of [HuggingFaceM4/idefics2-8b-base](https://huggingface.co/HuggingFaceM4/idefics2-8b-base). Refer to the original model's card for more information (including inference snippet).
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<fake_token_around_image>": 32000,
3
+ "<image>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Idefics2ForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 32001,
6
+ "model_type": "idefics2",
7
+ "perceiver_config": {
8
+ "model_type": "idefics2"
9
+ },
10
+ "quantization_config": {
11
+ "bits": 4,
12
+ "group_size": 128,
13
+ "modules_to_not_convert": ["model.vision_model", "model.modality_projection", "model.perceiver_resampler"],
14
+ "quant_method": "awq",
15
+ "version": "gemm",
16
+ "zero_point": true
17
+ },
18
+ "text_config": {
19
+ "max_position_embeddings": 32768,
20
+ "model_type": "mistral",
21
+ "pad_token_id": 0,
22
+ "rms_norm_eps": 1e-05,
23
+ "vocab_size": 32002
24
+ },
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.39.0.dev0",
28
+ "use_cache": true,
29
+ "vision_config": {
30
+ "hidden_size": 1152,
31
+ "image_size": 980,
32
+ "intermediate_size": 4304,
33
+ "model_type": "idefics2",
34
+ "num_attention_heads": 16,
35
+ "num_hidden_layers": 27,
36
+ "patch_size": 14
37
+ }
38
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 32000
6
+ ],
7
+ [
8
+ 32001
9
+ ]
10
+ ],
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "pad_token_id": 0,
14
+ "transformers_version": "4.39.0.dev0"
15
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9215c27257b7d4d30e16e62542b705506119af5305bc1ae23d69861545297c4c
3
+ size 4985988208
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a9c3678e94a2f953c0a73db7631cd7cc82e94b7e05edd2b5e26c665b21e058
3
+ size 1487017424
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_image_splitting": false,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Idefics2ImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Idefics2Processor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 980,
24
+ "shortest_edge": 378
25
+ }
26
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_len": 64,
3
+ "processor_class": "Idefics2Processor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<fake_token_around_image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<image>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "unk_token": {
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ }
46
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<fake_token_around_image>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<image>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<fake_token_around_image>",
48
+ "<image>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "clean_up_tokenization_spaces": false,
52
+ "eos_token": "</s>",
53
+ "legacy": false,
54
+ "model_max_length": 1000000000000000019884624838656,
55
+ "pad_token": "<unk>",
56
+ "processor_class": "Idefics2Processor",
57
+ "sp_model_kwargs": {},
58
+ "spaces_between_special_tokens": false,
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "unk_token": "<unk>",
61
+ "use_default_system_prompt": true
62
+ }