|
{ |
|
"_name_or_path": "/home/wenhao/Project/intern/xiapeng/rein/LLaVA-Med/checkpoint/llava-med-v1.5-mistral-7b", |
|
"architectures": [ |
|
"LlavaMistralForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"feature_outs": "encoder+decoder", |
|
"freeze_mm_mlp_adapter": false, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"image_aspect_ratio": "pad", |
|
"img_size": 640, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"max_position_embeddings": 32768, |
|
"mm_hidden_size": 1024, |
|
"mm_patch_merge_type": "flat", |
|
"mm_projector_lr": 2e-05, |
|
"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_llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 8, |
|
"pretraining_tp": 1, |
|
"proj_vis_to_txt_tokens": false, |
|
"prompt_segtok_w_instruct": false, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 1000000.0, |
|
"segtok_posembed": "sincos", |
|
"sliding_window": null, |
|
"tie_word_embeddings": false, |
|
"tokenizer_model_max_length": 1024, |
|
"tokenizer_padding_side": "right", |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.34.1", |
|
"tune_mm_mlp_adapter": false, |
|
"tune_vision_tokenizer": "none", |
|
"use_cache": true, |
|
"use_mm_proj": true, |
|
"vision_backbone": "convnextlarge", |
|
"vision_tokenizer_lr": null, |
|
"vocab_size": 32000 |
|
} |
|
|