Image-Text-to-Text
Transformers
Safetensors
English
idefics2
pretraining
multimodal
vision
Inference Endpoints
5 papers
idefics2-8b / config.json
VictorSanh's picture
VictorSanh HF staff
fix
8a0f3fa
{
"architectures": [
"Idefics2ForConditionalGeneration"
],
"image_token_id": 32001,
"model_type": "idefics2",
"perceiver_config": {
"model_type": "idefics2"
},
"text_config": {
"max_position_embeddings": 32768,
"model_type": "mistral",
"pad_token_id": 0,
"rms_norm_eps": 1e-05,
"vocab_size": 32003
},
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.39.0.dev0",
"use_cache": true,
"vision_config": {
"hidden_size": 1152,
"image_size": 980,
"intermediate_size": 4304,
"model_type": "idefics2",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"patch_size": 14
}
}