| { | |
| "_name_or_path": "./checkpoints/tiny-llava-stablelm-sharegpt4v-unlock-vit-from-12-siglip-stablelm-2-zephyr-1_6b-siglip-so400m-patch14-384-pretrain", | |
| "architectures": [ | |
| "LlavaStablelmForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "stabilityai/stablelm-2-zephyr-1_6b--configuration_stablelm_epoch.StableLMEpochConfig", | |
| "AutoModelForCausalLM": "stabilityai/stablelm-2-zephyr-1_6b--modeling_stablelm_epoch.StableLMEpochForCausalLM" | |
| }, | |
| "bos_token_id": 100257, | |
| "eos_token_id": 100257, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "image_aspect_ratio": "pad", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5632, | |
| "max_position_embeddings": 4096, | |
| "mm_hidden_size": 1152, | |
| "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": "./checkpoints/tiny-llava-stablelm-sharegpt4v-unlock-vit-from-12-siglip-stablelm-2-zephyr-1_6b-siglip-so400m-patch14-384-pretrain/vision_tower", | |
| "model_type": "llava_stablelm", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 32, | |
| "num_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 32, | |
| "pad_token": "<|endoftext|>", | |
| "pad_token_id": 100257, | |
| "rope_pct": 0.25, | |
| "rope_theta": 10000, | |
| "rotary_scaling_factor": 1.0, | |
| "tie_word_embeddings": false, | |
| "tokenizer_model_max_length": 2048, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.2", | |
| "tune_embed_tokens": false, | |
| "tune_entire_model": false, | |
| "tune_mm_mlp_adapter": false, | |
| "tune_vision_tower": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "use_qkv_bias": true, | |
| "vocab_size": 100352 | |
| } | |