CoolFace
Modelpublic

second-state/C4AI-Command-R-v01-GGUF

sourceHugging Facecc-by-nc-4.0updated 2y agoView on Hugging Face
1likes1.1kdownloads
Model Card

<!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end -->

C4AI-Command-R-v01-GGUF

Original Model

CohereForAI/c4ai-command-r-v01

Run with LlamaEdge

  • —LlamaEdge version: coming soon
  • —Context size: 8192

Quantized GGUF Models

NameQuant methodBitsSizeUse case
c4ai-command-r-v01-Q2_K.ggufQ2_K213.8 GBsmallest, significant quality loss - not recommended for most purposes
c4ai-command-r-v01-Q3_K_L.ggufQ3KL319.1 GBsmall, substantial quality loss
c4ai-command-r-v01-Q3_K_M.ggufQ3KM317.6 GBvery small, high quality loss
c4ai-command-r-v01-Q3_K_S.ggufQ3KS315.9 GBvery small, high quality loss
c4ai-command-r-v01-Q4_0.ggufQ4_0420.2 GBlegacy; small, very high quality loss - prefer using Q3KM
c4ai-command-r-v01-Q4_K_M.ggufQ4KM421.5 GBmedium, balanced quality - recommended
c4ai-command-r-v01-Q4_K_S.ggufQ4KS420.4 GBsmall, greater quality loss
c4ai-command-r-v01-Q5_0.ggufQ5_0524.3 GBlegacy; medium, balanced quality - prefer using Q4KM
c4ai-command-r-v01-Q5_K_M.ggufQ5KM525 GBlarge, very low quality loss - recommended
c4ai-command-r-v01-Q5_K_S.ggufQ5KS524.3 GBlarge, low quality loss - recommended
c4ai-command-r-v01-Q6_K.ggufQ6_K628.7 GBvery large, extremely low quality loss
c4ai-command-r-v01-Q8_0.ggufQ8_0837.2 GBvery large, extremely low quality loss - not recommended

Quantized with llama.cpp b2450