Hugging Face's logo

microsoft
/
git-large-textvqa

Visual Question Answering
Transformers
PyTorch
Safetensors
English
git
image-text-to-text
vision
Model card Files Community
1
nielsr HF staff commited on
Commit
a37bdb8
•
1 Parent(s): b8a66db

Upload GitForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +106 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "GitForCausalLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 101,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 102,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 1024,
17
+ "model_type": "git",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "num_image_with_embedding": null,
21
+ "pad_token_id": 0,
22
+ "position_embedding_type": "absolute",
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": null,
26
+ "use_cache": true,
27
+ "vision_config": {
28
+ "_name_or_path": "",
29
+ "add_cross_attention": false,
30
+ "architectures": null,
31
+ "attention_dropout": 0.0,
32
+ "bad_words_ids": null,
33
+ "begin_suppress_tokens": null,
34
+ "bos_token_id": null,
35
+ "chunk_size_feed_forward": 0,
36
+ "cross_attention_hidden_size": null,
37
+ "decoder_start_token_id": null,
38
+ "diversity_penalty": 0.0,
39
+ "do_sample": false,
40
+ "dropout": 0.0,
41
+ "early_stopping": false,
42
+ "encoder_no_repeat_ngram_size": 0,
43
+ "eos_token_id": null,
44
+ "exponential_decay_length_penalty": null,
45
+ "finetuning_task": null,
46
+ "forced_bos_token_id": null,
47
+ "forced_eos_token_id": null,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "id2label": {
51
+ "0": "LABEL_0",
52
+ "1": "LABEL_1"
53
+ },
54
+ "image_size": 420,
55
+ "initializer_factor": 1.0,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "is_decoder": false,
59
+ "is_encoder_decoder": false,
60
+ "label2id": {
61
+ "LABEL_0": 0,
62
+ "LABEL_1": 1
63
+ },
64
+ "layer_norm_eps": 1e-05,
65
+ "length_penalty": 1.0,
66
+ "max_length": 20,
67
+ "min_length": 0,
68
+ "model_type": "git_vision_model",
69
+ "no_repeat_ngram_size": 0,
70
+ "num_attention_heads": 16,
71
+ "num_beam_groups": 1,
72
+ "num_beams": 1,
73
+ "num_channels": 3,
74
+ "num_hidden_layers": 24,
75
+ "num_return_sequences": 1,
76
+ "output_attentions": false,
77
+ "output_hidden_states": false,
78
+ "output_scores": false,
79
+ "pad_token_id": null,
80
+ "patch_size": 14,
81
+ "prefix": null,
82
+ "problem_type": null,
83
+ "projection_dim": 512,
84
+ "pruned_heads": {},
85
+ "remove_invalid_values": false,
86
+ "repetition_penalty": 1.0,
87
+ "return_dict": true,
88
+ "return_dict_in_generate": false,
89
+ "sep_token_id": null,
90
+ "suppress_tokens": null,
91
+ "task_specific_params": null,
92
+ "temperature": 1.0,
93
+ "tf_legacy_loss": false,
94
+ "tie_encoder_decoder": false,
95
+ "tie_word_embeddings": true,
96
+ "tokenizer_class": null,
97
+ "top_k": 50,
98
+ "top_p": 1.0,
99
+ "torch_dtype": null,
100
+ "torchscript": false,
101
+ "transformers_version": "4.26.0.dev0",
102
+ "typical_p": 1.0,
103
+ "use_bfloat16": false
104
+ },
105
+ "vocab_size": 30522
106
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84cd56d1a6da7c53f2364e786c7f7578604112378b42c9e4aafba7bf5336075c
3
+ size 1579609049