| { | |
| "video_model_name_or_path":"Chat-UniVi/Chat-UniVi", | |
| "dynamicrafter": "./DynamiCrafter/configs/inference_512_v1.0.yaml", | |
| "diffusion_model_name_or_path":"stabilityai/stable-diffusion-2-base", | |
| "image_prefix_length": 64, | |
| "use_diffusion_text_encoder": false, | |
| "video_model_config": | |
| { | |
| "_name_or_path": "", | |
| "aarchitectures": "ChatUniViLlamaForCausalLM", | |
| "architectures": [ | |
| "ChatUniViLlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "config": { | |
| "spatial_cluster_rate0": 64, | |
| "spatial_cluster_rate1": 32, | |
| "spatial_cluster_rate2": 16, | |
| "freeze": false, | |
| "mm_tune": true, | |
| "use_cluster": true, | |
| "temporal_cluster_rate": 0.0625, | |
| "vision_tune": false | |
| }, | |
| "eos_token_id": 2, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "image_aspect_ratio": "square", | |
| "image_grid_pinpoints": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "mm_hidden_size": 1024, | |
| "mm_use_box_start_end": false, | |
| "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", | |
| "model_type": "ChatUniVi", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.31.0", | |
| "tune_mm_mlp_adapter": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vocab_size": 32000 | |
| }, | |
| "use_image_prefix": true, | |
| "use_flash_attn": false, | |
| "use_image_callbacks": false, | |
| "rescale_betas_zero_snr": true, | |
| "parameterization": "v", | |
| "linear_start": 0.00085, | |
| "linear_end": 0.012, | |
| "num_timesteps_cond": 1, | |
| "timesteps": 1000, | |
| "first_stage_key": "video", | |
| "cond_stage_key": "caption", | |
| "cond_stage_trainable": false, | |
| "conditioning_key": "hybrid", | |
| "image_size": [ | |
| 40, | |
| 64 | |
| ], | |
| "channels": 4, | |
| "scale_by_std": false, | |
| "scale_factor": 0.18215, | |
| "use_ema": false, | |
| "uncond_type": "empty_seq", | |
| "use_dynamic_rescale": true, | |
| "base_scale": 0.7, | |
| "fps_condition_type": "fps", | |
| "perframe_ae": true, | |
| "qformer_config":{ | |
| "model_name": "blip_2_qformer" | |
| }, | |
| "diffusion_qformer_config":{ | |
| "hidden_size": 768 | |
| } | |
| } |