--- language: - en base_model: - mistralai/Mistral-7B-Instruct-v0.2 pipeline_tag: video-text-to-text library_name: transformers --- # Infinite-VideoChat2 HuggingFace-compatible model files for **VideoChat2-Infinity** (Mistral-7B), a long video understanding model that extends [VideoChat2-HD](https://github.com/OpenGVLab/Ask-Anything/tree/main/video_chat2) with infinite-length video processing via continuous long-term attention. ## Model Architecture - **Vision Encoder** – UMT-L (ViT, 1024-dim, 24 layers) - **Q-Former** – bridges visual features to the LLM with 32 + 64 query tokens - **LLM** – [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) - **Long-Term Attention** – Gibbs-sampling-based continuous attention over basis functions for unbounded temporal context ## File Overview | File | Description | |------|-------------| | `config.json` | HuggingFace `AutoConfig` configuration | | `configuration_videochat2.py` | Custom `PretrainedConfig` subclass (`Config`) | | `videochat2_it_hd_mistral.py` | Main model class (`VideoChat2_it_hd_mistral`) | | `blip2.py` | BLIP-2 base class for vision-language bridging | | `vit.py` | Vision Transformer (UMT-L) implementation | | `Qformer.py` | Q-Former module | | `basis_functions.py` | Basis functions (Power, Sine, Cosine, Gaussian, Rectangular) for long-term attention | | `long_term_attention_gibbs.py` | Long-term attention with Gibbs sampling | | `model-*.safetensors` | Model weights (sharded, 4 parts) | | `.gitignore` | Ignores model weight files | ## Usage The model is registered with HuggingFace `auto_map`, so it can be loaded directly: ```python from transformers import AutoConfig, AutoModel config = AutoConfig.from_pretrained("Rihong/VideoChat2_Infinity_Mistral_7B_hf", trust_remote_code=True) model = AutoModel.from_pretrained("Rihong/VideoChat2_Infinity_Mistral_7B_hf", trust_remote_code=True) ``` To upload model to HuggingFace, just run: ```bash hf upload Rihong/VideoChat2_Infinity_Mistral_7B_hf ./lmms_eval/baselines/infty_videochat2/ ``` ## Key Hyperparameters | Parameter | Default | Description | |-----------|---------|-------------| | `num_basis` | 256 | Number of basis functions for long-term attention | | `tau` | 0.75 | Temperature for Gibbs sampling | | `alpha` | 0.75 | Mixing coefficient | | `sticky` | `true` | Enable sticky memories | | `hd_num` | 6 | Number of high-definition crops | | `local_size` | 224 | Local crop resolution | ## References - [VideoChat2 (Ask-Anything)](https://github.com/OpenGVLab/Ask-Anything/tree/main/video_chat2) - [Infinite-Video](https://github.com/deep-spin/Infinite-Video)