|
{ |
|
"_name_or_path": "/comp_robot/zhanghao/ckpts/vicuna/vicuna-7b-v1.3/", |
|
"architectures": [ |
|
"LlavaLlamaForCausalLM_joint_2st_it_only_ref_instr" |
|
], |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"freeze_mm_mlp_adapter": false, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"image_aspect_ratio": "square", |
|
"image_grid_pinpoints": null, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"max_position_embeddings": 2048, |
|
"mm_hidden_size": 1024, |
|
"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", |
|
"model_type": "llava", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"pad_token_id": 0, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-06, |
|
"rope_scaling": null, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.31.0", |
|
"tune_mm_mlp_adapter": false, |
|
"tune_prompt_adapter": true, |
|
"use_cache": true, |
|
"use_mm_proj": true, |
|
"vocab_size": 32003 |
|
} |
|
|