Text Generation
Transformers
Safetensors
English
llava_phi
custom_code
ALLaVA-3B-Longer / config.json
g-h-chen's picture
upload config.json
798c126 verified
raw
history blame
1.41 kB
{
"_name_or_path": "FreedomIntelligence/ALLaVA-3B-Longer",
"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,
"flash_attn": true,
"flash_rotary": true,
"fused_dense": true,
"hidden_act": "gelu_new",
"hidden_size": 2560,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 10240,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"mm_hidden_size": 1024,
"mm_projector_lr": null,
"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": "llava_phi",
"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,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0.dev0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 51200
}