전체 검색

AI 모델 84759

• muse-wonder-1.0↗

  待核实厂商

  Muse Wonder는 Meta의 가장 강력한 모델(프리뷰 버전)로, 복잡한 소프트웨어 엔지니어링 및 장시간 실행되는 에이전트 작업을 위해 설계되었습니다. 여러 파일에 걸쳐 코드를 수정하고 검증하며, 하위 에이전트를 스케줄링하고, 도구를 병렬로 호출하며 컴퓨터를 조작할 수 있습니다. 또한 이미지, 비디오, 오디오 및 PDF 입력을 지원하며, 100만 토큰 규모의 컨텍스트를 처리합니다.

• LumiPic↗

  oumoumad

• babylm_2025_submission_strict↗

  PatrickHaller

• StableBeluga2↗

  petals-team

  This repository contains the model from the stabilityai/StableBeluga2 repository with the following changes: 1. **Storing weights in `bfloat16` instead of `float32`.** This leads to 2x smaller files and a small quality loss, which is not significant compared to the loss caused by NF4 quantization used in Petals by default. 1. **Storing weights in small shards.** Each transformer block is stored in its own shard (1.71 GB each). The input and output embeddings and adjacent layernorms are in a separate shard (1.05 GB) too. This way, Petals clients and servers don't have to download any excess data besides the layers they actually use. 1. **Using Safetensors instead of Pickle.** This allows faster loading with smaller RAM requirements. We provide the original README below. Please refer there for model details and licensing information.

• Hemmingway-1.5-SSMFIX-APOSTATE↗

  Phil2Sat

• Gliese-Query_Tool-0.6B-GGUF↗

  prithivMLmods

• Qwen3-VisionCaption-2B-GGUF↗

  prithivMLmods

• granite-3.0-1b-a400m-base-GGUF↗

  QuantFactory

• SmolLM-360M-GGUF↗

  QuantFactory

• agent-husky_-_husky-v1-math-deepseekmath-7b-instruct-gguf↗

  RichardErkhov