echarlaix HF Staff commited on
Commit
3b32b1b
·
verified ·
1 Parent(s): f735f89

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +157 -0
config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Idefics3ForConditionalGeneration"
5
+ ],
6
+ "image_token_id": 49190,
7
+ "model_type": "idefics3",
8
+ "pad_token_id": 128002,
9
+ "scale_factor": 4,
10
+ "text_config": {
11
+ "_flash_attn_2_enabled": true,
12
+ "_name_or_path": "None",
13
+ "architectures": [
14
+ "VLlama3ForCausalLM"
15
+ ],
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "head_dim": 64,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 576,
21
+ "initializer_range": 0.041666666666666664,
22
+ "intermediate_size": 1536,
23
+ "is_llama_config": true,
24
+ "max_position_embeddings": 8192,
25
+ "mlp_bias": false,
26
+ "model_type": "llama",
27
+ "neftune_noise_alpha": 0.0,
28
+ "num_attention_heads": 9,
29
+ "num_hidden_layers": 30,
30
+ "num_key_value_heads": 3,
31
+ "pad_token_id": 2,
32
+ "perceiver_config": {
33
+ "_attn_implementation_autoset": false,
34
+ "_name_or_path": "",
35
+ "add_cross_attention": false,
36
+ "architectures": null,
37
+ "attention_dropout": 0.0,
38
+ "bad_words_ids": null,
39
+ "begin_suppress_tokens": null,
40
+ "bos_token_id": null,
41
+ "chunk_size_feed_forward": 0,
42
+ "cross_attention_hidden_size": null,
43
+ "decoder_start_token_id": null,
44
+ "diversity_penalty": 0.0,
45
+ "do_sample": false,
46
+ "early_stopping": false,
47
+ "encoder_no_repeat_ngram_size": 0,
48
+ "eos_token_id": null,
49
+ "exponential_decay_length_penalty": null,
50
+ "finetuning_task": null,
51
+ "forced_bos_token_id": null,
52
+ "forced_eos_token_id": null,
53
+ "hidden_act": "silu",
54
+ "id2label": {
55
+ "0": "LABEL_0",
56
+ "1": "LABEL_1"
57
+ },
58
+ "is_decoder": false,
59
+ "is_encoder_decoder": false,
60
+ "label2id": {
61
+ "LABEL_0": 0,
62
+ "LABEL_1": 1
63
+ },
64
+ "length_penalty": 1.0,
65
+ "max_length": 20,
66
+ "min_length": 0,
67
+ "model_type": "vllama3",
68
+ "no_repeat_ngram_size": 0,
69
+ "num_beam_groups": 1,
70
+ "num_beams": 1,
71
+ "num_key_value_heads": 1,
72
+ "num_return_sequences": 1,
73
+ "output_attentions": false,
74
+ "output_hidden_states": false,
75
+ "output_scores": false,
76
+ "pad_token_id": null,
77
+ "prefix": null,
78
+ "problem_type": null,
79
+ "pruned_heads": {},
80
+ "qk_layer_norms_perceiver": false,
81
+ "remove_invalid_values": false,
82
+ "repetition_penalty": 1.0,
83
+ "resampler_depth": 6,
84
+ "resampler_head_dim": 96,
85
+ "resampler_n_heads": 16,
86
+ "resampler_n_latents": 64,
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": "4.46.0",
102
+ "typical_p": 1.0,
103
+ "use_bfloat16": false
104
+ },
105
+ "pixel_shuffle_factor": 4,
106
+ "pretraining_tp": 1,
107
+ "qk_layer_norms": false,
108
+ "rms_norm_eps": 1e-05,
109
+ "rope_interleaved": false,
110
+ "rope_scaling": null,
111
+ "rope_theta": 100000,
112
+ "torch_dtype": "bfloat16",
113
+ "transformers.js_config": {
114
+ "kv_cache_dtype": {
115
+ "fp16": "float16",
116
+ "q4f16": "float16"
117
+ }
118
+ },
119
+ "use_cache": true,
120
+ "use_resampler": false,
121
+ "vocab_size": 49280
122
+ },
123
+ "tie_word_embeddings": false,
124
+ "torch_dtype": "bfloat16",
125
+ "transformers.js_config": {
126
+ "kv_cache_dtype": {
127
+ "fp16": "float16",
128
+ "q4f16": "float16"
129
+ }
130
+ },
131
+ "transformers_version": "4.51.3",
132
+ "use_cache": true,
133
+ "vision_config": {
134
+ "attention_dropout": 0.0,
135
+ "hidden_act": "gelu_pytorch_tanh",
136
+ "hidden_size": 768,
137
+ "image_size": 512,
138
+ "initializer_range": 0.02,
139
+ "intermediate_size": 3072,
140
+ "layer_norm_eps": 1e-06,
141
+ "max_image_size": {
142
+ "longest_edge": 512
143
+ },
144
+ "model_type": "idefics3_vision",
145
+ "num_attention_heads": 12,
146
+ "num_channels": 3,
147
+ "num_hidden_layers": 12,
148
+ "patch_size": 16,
149
+ "size": {
150
+ "longest_edge": 2048
151
+ },
152
+ "tie_word_embeddings": false,
153
+ "torch_dtype": "bfloat16",
154
+ "use_base_siglip": true
155
+ },
156
+ "vocab_size": 49280
157
+ }