| { |
| "_attn_implementation_autoset": true, |
| "architectures": [ |
| "LlavaMistralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "feature_outs": "encoder+decoder", |
| "freeze_mm_mlp_adapter": false, |
| "head_dim": 128, |
| "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_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_mistral", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "proj_vis_to_txt_tokens": false, |
| "prompt_segtok_w_instruct": false, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 1000000.0, |
| "segtok_posembed": "sincos", |
| "sliding_window": 512, |
| "tie_word_embeddings": false, |
| "tokenizer_model_max_length": 2048, |
| "tokenizer_padding_side": "right", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.3", |
| "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 |
| } |
|
|
