hugpadhugpad

InferenceIllusionist / Meta-Llama-3.1-8B-Claude-iMat-GGUF

Other1.4K13Updated Jul 29, 2024
Hugging Face

Downloads

1.4K

Likes

13

Last updated

Jul 29, 2024

License

Not available

Quantized from Meta-Llama-3.1-8B-Claude fp16 Weighted quantizations were creating using fp16 GGUF and groupsmerged.txt in 88 chunks and nctx=512 Static fp16 will also be included in repo For a brief rundown of iMatrix quant performance please see this PR <iAll quants are verif…

Tasks & library

  • transformers

Tags

  • transformers
  • gguf
  • iMat
  • llama3
  • conversational

Technical specifications

ParametersNot available
Librarytransformers
LanguagesNot available
Base modelUndi95/Meta-Llama-3.1-8B-Claude
LicenseNot available