hf-transformers-bot's picture
Update tiny models for IdeficsForVisionText2Text
cea9674 verified
Raw
History Blame Contribute Delete
1.89 kB
{
"additional_vocab_size": 0,
"alpha_initializer": "ones",
"alpha_type": "float",
"alphas_initializer_range": 0.0,
"architectures": [
"IdeficsForVisionText2Text"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 1,
"cross_layer_interval": 1,
"dropout": 0.0,
"dtype": "float32",
"eos_token_id": 2,
"freeze_lm_head": false,
"freeze_text_layers": true,
"freeze_text_module_exceptions": [],
"freeze_vision_layers": true,
"freeze_vision_module_exceptions": [],
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 32,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"image_size": 30,
"initializer_range": 0.02,
"intermediate_size": 37,
"is_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"max_position_embeddings": 512,
"modality_type_vocab_size": 2,
"model_type": "idefics",
"num_attention_heads": 4,
"num_channels": 3,
"num_hidden_layers": 2,
"pad_token_id": 0,
"patch_size": 2,
"perceiver_config": {
"model_type": "idefics_perciever",
"qk_layer_norms_perceiver": false,
"resampler_depth": 6,
"resampler_head_dim": 96,
"resampler_n_heads": 16,
"resampler_n_latents": 64,
"use_resampler": false
},
"qk_layer_norms": false,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"transformers_version": "5.16.0.dev0",
"type_vocab_size": 16,
"use_cache": true,
"use_resampler": false,
"vision_config": {
"attention_dropout": 0.0,
"embed_dim": 32,
"hidden_act": "gelu",
"image_size": 30,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 37,
"layer_norm_eps": 1e-05,
"model_type": "idefics_vision",
"num_attention_heads": 4,
"num_channels": 3,
"num_hidden_layers": 2,
"patch_size": 2
},
"vocab_size": 32002
}