| { | |
| "_name_or_path": "bczhou/TinyLLaVA-3.1B", | |
| "architectures": [ | |
| "TinyLlavaPhiForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig", | |
| "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM" | |
| }, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 50256, | |
| "freeze_mm_mlp_adapter": false, | |
| "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": 1152, | |
| "mm_patch_merge_type": "flat", | |
| "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": "bczhou/TinyLLaVA-3.1B-SigLIP", | |
| "model_type": "tiny_llava_phi", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token": "<|endoftext|>", | |
| "pad_token_id": 50256, | |
| "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": 3072, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.40.0", | |
| "tune_embed_tokens": false, | |
| "tune_entire_model": false, | |
| "tune_mm_mlp_adapter": false, | |
| "tune_vision_tower": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vocab_size": 51200 | |
| } | |