Team Ai
Modelpublic

second-state/Yi-Coder-9B-Chat-GGUF

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes599downloads
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 -->

Yi-Coder-9B-Chat-GGUF

Original Model

01-ai/Yi-Coder-9B-Chat

Run with LlamaEdge

  • —LlamaEdge version: v0.14.2 and above
  • —Prompt template
  • —Prompt type: chatml
  • —Prompt string
text
    <|im_start|>system
    {system_message}<|im_end|>
    <|im_start|>user
    {prompt}<|im_end|>
    <|im_start|>assistant
  • —Reverse prompt: <|im_end|>
  • —Context size: 128000
  • —Run as LlamaEdge service
bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-Coder-9B-Chat-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template chatml \
    --reverse-prompt "<|im_end|>" \
    --ctx-size 128000 \
    --model-name Yi-Coder-9B-Chat
  • —Run as LlamaEdge command app
bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-Coder-9B-Chat-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template chatml \
    --reverse-prompt "<|im_end|>" \
    --ctx-size 128000

Quantized GGUF Models

NameQuant methodBitsSizeUse case
Yi-Coder-9B-Chat-Q2_K.ggufQ2_K23.35 GBsmallest, significant quality loss - not recommended for most purposes
Yi-Coder-9B-Chat-Q3_K_L.ggufQ3KL34.69 GBsmall, substantial quality loss
Yi-Coder-9B-Chat-Q3_K_M.ggufQ3KM34.32 GBvery small, high quality loss
Yi-Coder-9B-Chat-Q3_K_S.ggufQ3KS33.90 GBvery small, high quality loss
Yi-Coder-9B-Chat-Q4_0.ggufQ4_045.04 GBlegacy; small, very high quality loss - prefer using Q3KM
Yi-Coder-9B-Chat-Q4_K_M.ggufQ4KM45.33 GBmedium, balanced quality - recommended
Yi-Coder-9B-Chat-Q4_K_S.ggufQ4KS45.07 GBsmall, greater quality loss
Yi-Coder-9B-Chat-Q5_0.ggufQ5_056.11 GBlegacy; medium, balanced quality - prefer using Q4KM
Yi-Coder-9B-Chat-Q5_K_M.ggufQ5KM56.26 GBlarge, very low quality loss - recommended
Yi-Coder-9B-Chat-Q5_K_S.ggufQ5KS56.11 GBlarge, low quality loss - recommended
Yi-Coder-9B-Chat-Q6_K.ggufQ6_K67.25 GBvery large, extremely low quality loss
Yi-Coder-9B-Chat-Q8_0.ggufQ8_089.38 GBvery large, extremely low quality loss - not recommended
Yi-Coder-9B-Chat-f16.gguff161617.7 GB

Quantized with llama.cpp b3664