awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetServeur MCPÀ proposNotre méthodologiePresse
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

2 dépôts

Awesome GitHub RepositoriesContext Window Extenders

Generates long video sequences by processing overlapping frame windows to produce high-frame-count outputs with limited VRAM.

Distinct from Video Frame Processing: Distinct from Video Frame Processing: extends video length via overlapping windows rather than decoding or adjusting individual frames.

Explore 2 awesome GitHub repositories matching graphics & multimedia · Context Window Extenders. Refine with filters or upvote what's useful.

Awesome Context Window Extenders GitHub Repositories

Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
  • kijai/comfyui-wanvideowrapperAvatar de kijai

    kijai/ComfyUI-WanVideoWrapper

    6,554Voir sur GitHub↗

    I've made everythign less reliant on torch.compile for VRAM efficiency, so things should work better even without it. Also figured workaround for some issues when using compile that made first run use drastically more VRAM, issue I battled with myself a lot.

    Implements context-window video extension that processes overlapping frame windows to generate long sequences under VRAM constraints.

    Python
    Voir sur GitHub↗6,554
  • baichuan-inc/baichuan-7bAvatar de baichuan-inc

    baichuan-inc/Baichuan-7B

    5,654Voir sur GitHub↗

    Baichuan-7B is an open-source 7 billion parameter bilingual Transformer model designed for text generation and few-shot learning across Chinese and English. It is built on a large Transformer architecture trained on a bilingual corpus, enabling it to produce coherent text in both languages from a single model. The model incorporates several optimization techniques that distinguish it from standard large language models. It uses rotary position embeddings that can extrapolate to longer sequences than seen during training, allowing context extension beyond the original 4096-token training lengt

    Extends context beyond training length by using rotary position embeddings that generalize to longer sequences.

    Pythonartificial-intelligencecevalchatgpt
    Voir sur GitHub↗5,654
  1. Home
  2. Graphics & Multimedia
  3. Video Frame Processing
  4. Context Window Extenders

Explorer les sous-tags

  • Rotary Context ExtrapolatorsExtending context windows beyond training length using rotary position embeddings that generalize to longer sequences. **Distinct from Context Window Extenders:** Distinct from Context Window Extenders: uses rotary position embedding extrapolation for text, not overlapping video frame windows.