| { | |
| "_name_or_path": "/ib-scratch/chenguang03/vision_share/models/llava-gemma2", | |
| "architectures": [ | |
| "TALlavaGemmaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": 50.0, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "eos_token_id": [ | |
| 1, | |
| 107 | |
| ], | |
| "final_logit_softcapping": 30.0, | |
| "freeze_mm_mlp_adapter": false, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2304, | |
| "image_aspect_ratio": "pad", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "max_position_embeddings": 8192, | |
| "mm_hidden_size": 1024, | |
| "mm_patch_merge_type": "flat", | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "linear", | |
| "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": "tallava_gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 4, | |
| "num_learnable_tokens": 32, | |
| "pad_token_id": 0, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tokenizer_model_max_length": 2048, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.2", | |
| "tune_mm_mlp_adapter": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vocab_size": 256000 | |
| } | |