CoolFace
Modelpublic

second-state/ChatAllInOne-Yi-34B-200K-V1-GGUF

sourceHugging Faceotherupdated 3y agoView on Hugging Face
0likes1.4kdownloads
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 -->

ChatAllInOne-Yi-34B-200K-V1-GGUF

Original Model

DrNicefellow/ChatAllInOne-Yi-34B-200K-V1

Run with LlamaEdge

  • —LlamaEdge version: coming soon
  • —Prompt template
  • —Prompt type: vicuna-1.1-chat
  • —Prompt string
text
    USER: {prompt}
    ASSISTANT:
  • —Context size: 7168

<!-- - Run as LlamaEdge service

bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:openchat-3.5-0106-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:openchat-3.5-0106-Q5_K_M.gguf llama-chat.wasm -p openchat -r '<|end_of_turn|>'

Quantized GGUF Models

NameQuant methodBitsSizeUse case
ChatAllInOne-Yi-34B-200K-V1-Q2_K.ggufQ2_K212.8 GBsmallest, significant quality loss - not recommended for most purposes
ChatAllInOne-Yi-34B-200K-V1-Q3_K_L.ggufQ3KL318.1 GBsmall, substantial quality loss
ChatAllInOne-Yi-34B-200K-V1-Q3_K_M.ggufQ3KM316.7 GBvery small, high quality loss
ChatAllInOne-Yi-34B-200K-V1-Q3_K_S.ggufQ3KS315 GBvery small, high quality loss
ChatAllInOne-Yi-34B-200K-V1-Q4_0.ggufQ4_0419.5 GBlegacy; small, very high quality loss - prefer using Q3KM
ChatAllInOne-Yi-34B-200K-V1-Q4_K_M.ggufQ4KM420.7 GBmedium, balanced quality - recommended
ChatAllInOne-Yi-34B-200K-V1-Q4_K_S.ggufQ4KS419.6 GBsmall, greater quality loss
ChatAllInOne-Yi-34B-200K-V1-Q5_0.ggufQ5_0523.7 GBlegacy; medium, balanced quality - prefer using Q4KM
ChatAllInOne-Yi-34B-200K-V1-Q5_K_M.ggufQ5KM524.3 GBlarge, very low quality loss - recommended
ChatAllInOne-Yi-34B-200K-V1-Q5_K_S.ggufQ5KS523.7 GBlarge, low quality loss - recommended
ChatAllInOne-Yi-34B-200K-V1-Q6_K.ggufQ6_K628.2 GBvery large, extremely low quality loss
ChatAllInOne-Yi-34B-200K-V1-Q8_0.ggufQ8_0836.5 GBvery large, extremely low quality loss - not recommended

Quantized with llama.cpp b2334