GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — GitHub - Mainframework/Quanta: Convert and quantize llm models Folders and filesRepository files navigationConvert and quantize llm models This is an app for windows which allows power users to work with .safetensors models. 
It convert models in FP16 or FP32 quite fast It includes many type of quantization from: q4_k_m,q5_k_m,q6_k,q8_0, F16, BF16, F32, IQ4_NL... Requirements: Transformers, Torch, Sentencepiece. In cmd or powershell do: python -m pip install transformers python -m pip install torch python -m pip install sentencepiece AboutConvert and quantize llm models Topicsaiartificial-intelligenceawesome-aiawesome-ai-toolsbest-ai-softwarebest-appsbestofaibestofthebestggufgguf-editorgguf-model-supportgguf-modelsgguf-quantizationllmquantaquantizationsafetensorstop-ai-toolstop10top100 ResourcesReleasesPackagesContributorsLanguages |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |