Video-Text-to-Text
Transformers
Safetensors
sam2
English
vica_qwen
text-generation
multimodal
vision-language
video understanding
visuospatial cognition
spatial reasoning
vlm
llava
qwen
siglip
hiera
dual-encoder
Eval Results (legacy)
Instructions to use nkkbr/ViCA2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nkkbr/ViCA2 with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("nkkbr/ViCA2", device_map="auto") - sam2
How to use nkkbr/ViCA2 with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(nkkbr/ViCA2) with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)# Use SAM2 with videos import torch from sam2.sam2_video_predictor import SAM2VideoPredictor predictor = SAM2VideoPredictor.from_pretrained(nkkbr/ViCA2) with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): state = predictor.init_state(<your_video>) # add new prompts and instantly get the output on the same frame frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>): # propagate the prompts to get masklets throughout the video for frame_idx, object_ids, masks in predictor.propagate_in_video(state): ... - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "nkkbr/ViCA2", | |
| "add_faster_video": false, | |
| "add_time_instruction": true, | |
| "architectures": [ | |
| "VicaQwenForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "faster_token_stride": 10, | |
| "force_sample": true, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_aspect_ratio": "anyres_max_9", | |
| "image_crop_resolution": null, | |
| "image_grid_pinpoints": [ | |
| [ | |
| 384, | |
| 384 | |
| ], | |
| [ | |
| 384, | |
| 768 | |
| ], | |
| [ | |
| 384, | |
| 1152 | |
| ], | |
| [ | |
| 384, | |
| 1536 | |
| ], | |
| [ | |
| 384, | |
| 1920 | |
| ], | |
| [ | |
| 384, | |
| 2304 | |
| ], | |
| [ | |
| 768, | |
| 384 | |
| ], | |
| [ | |
| 768, | |
| 768 | |
| ], | |
| [ | |
| 768, | |
| 1152 | |
| ], | |
| [ | |
| 768, | |
| 1536 | |
| ], | |
| [ | |
| 768, | |
| 1920 | |
| ], | |
| [ | |
| 768, | |
| 2304 | |
| ], | |
| [ | |
| 1152, | |
| 384 | |
| ], | |
| [ | |
| 1152, | |
| 768 | |
| ], | |
| [ | |
| 1152, | |
| 1152 | |
| ], | |
| [ | |
| 1152, | |
| 1536 | |
| ], | |
| [ | |
| 1152, | |
| 1920 | |
| ], | |
| [ | |
| 1152, | |
| 2304 | |
| ], | |
| [ | |
| 1536, | |
| 384 | |
| ], | |
| [ | |
| 1536, | |
| 768 | |
| ], | |
| [ | |
| 1536, | |
| 1152 | |
| ], | |
| [ | |
| 1536, | |
| 1536 | |
| ], | |
| [ | |
| 1536, | |
| 1920 | |
| ], | |
| [ | |
| 1536, | |
| 2304 | |
| ], | |
| [ | |
| 1920, | |
| 384 | |
| ], | |
| [ | |
| 1920, | |
| 768 | |
| ], | |
| [ | |
| 1920, | |
| 1152 | |
| ], | |
| [ | |
| 1920, | |
| 1536 | |
| ], | |
| [ | |
| 1920, | |
| 1920 | |
| ], | |
| [ | |
| 1920, | |
| 2304 | |
| ], | |
| [ | |
| 2304, | |
| 384 | |
| ], | |
| [ | |
| 2304, | |
| 768 | |
| ], | |
| [ | |
| 2304, | |
| 1152 | |
| ], | |
| [ | |
| 2304, | |
| 1536 | |
| ], | |
| [ | |
| 2304, | |
| 1920 | |
| ], | |
| [ | |
| 2304, | |
| 2304 | |
| ] | |
| ], | |
| "image_split_resolution": null, | |
| "image_token_index": 151646, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "mm_hidden_size": 1152, | |
| "mm_newline_position": "grid", | |
| "mm_patch_merge_type": "spatial_unpad", | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_resampler_type": null, | |
| "mm_spatial_pool_mode": "bilinear", | |
| "mm_spatial_pool_stride": 2, | |
| "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model,sam_projector", | |
| "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": "google/siglip-so400m-patch14-384", | |
| "mm_vision_tower_lr": 2e-06, | |
| "model_type": "vica_qwen", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "pos_skipping_range": 4096, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": false, | |
| "tokenizer_model_max_length": 32768, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.0.dev0", | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "use_pos_skipping": false, | |
| "use_sliding_window": false, | |
| "vision_tower_pretrained": null, | |
| "vocab_size": 151647 | |
| } | |