CoolFace
Modelpublic

second-state/Starling-LM-7B-alpha-GGUF

sourceHugging Facecc-by-nc-4.0updated 3y agoView on Hugging Face
3likes694downloads
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 -->

Starling-LM-7B-alpha-GGUF

Original Model

berkeley-nest/Starling-LM-7B-alpha

Run with LlamaEdge

  • —LlamaEdge version: v0.2.8 and above
  • —Prompt template
  • —Prompt type: openchat
  • —Prompt string
text
    GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
  • —Reverse prompt: <|end_of_turn|>
  • —Context size: 4096
  • —Run as LlamaEdge service
bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:starling-lm-7b-alpha.Q5_K_M.gguf llama-api-server.wasm -p openchat -r '<|end_of_turn|>'
  • —Run as LlamaEdge command app
bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:starling-lm-7b-alpha.Q5_K_M.gguf llama-chat.wasm -p openchat -r '<|end_of_turn|>'

Quantized GGUF Models

NameQuant methodBitsSizeUse case
Starling-LM-7B-alpha-Q2_K.ggufQ2_K22.7 GBsmallest, significant quality loss - not recommended for most purposes
Starling-LM-7B-alpha-Q3_K_L.ggufQ3KL33.82 GBsmall, substantial quality loss
Starling-LM-7B-alpha-Q3_K_M.ggufQ3KM33.52 GBvery small, high quality loss
Starling-LM-7B-alpha-Q3_K_S.ggufQ3KS33.16 GBvery small, high quality loss
Starling-LM-7B-alpha-Q4_0.ggufQ4_044.11 GBlegacy; small, very high quality loss - prefer using Q3KM
Starling-LM-7B-alpha-Q4_K_M.ggufQ4KM44.37 GBmedium, balanced quality - recommended
Starling-LM-7B-alpha-Q4_K_S.ggufQ4KS44.14 GBsmall, greater quality loss
Starling-LM-7B-alpha-Q5_0.ggufQ5_055.00 GBlegacy; medium, balanced quality - prefer using Q4KM
Starling-LM-7B-alpha-Q5_K_M.ggufQ5KM55.13 GBlarge, very low quality loss - recommended
Starling-LM-7B-alpha-Q5_K_S.ggufQ5KS55.00 GBlarge, low quality loss - recommended
Starling-LM-7B-alpha-Q6_K.ggufQ6_K65.94 GBvery large, extremely low quality loss
Starling-LM-7B-alpha-Q8_0.ggufQ8_087.70 GBvery large, extremely low quality loss - not recommended