Text Generation
Transformers
Safetensors
English
phi-llava
custom_code
Inference Endpoints
llava-phi-2-3b / config.json
marianna13's picture
Upload LlavaPhiForCausalLM
f451880 verified
{
"_name_or_path": "/p/project/laionize/marianna/bakllava_original/llava-phi-2-3b",
"architectures": [
"LlavaPhiForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi.PhiConfig",
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
},
"bos_token_id": null,
"embd_pdrop": 0.0,
"eos_token_id": null,
"freeze_mm_mlp_adapter": false,
"hidden_act": "gelu_new",
"hidden_size": 2560,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 10240,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"mm_hidden_size": 1024,
"mm_projector_type": "mlp2x_gelu",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
"model_type": "phi-llava",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"partial_rotary_factor": 0.4,
"qk_layernorm": false,
"resid_pdrop": 0.1,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.37.0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 51200
}