Modelpublic

second-state/Zephyr-7B-Alpha-GGUF

sourceHugging Facemitupdated 3y agoView on Hugging Face

0likes719downloads

Model Card

<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;">

Zephyr-7B-Alpha-GGUF

Original Model

HuggingFaceH4/zephyr-7b-alpha

Run with LlamaEdge

—LlamaEdge version: v0.2.8 and above

—Prompt template

—Prompt type: zephyr

—Prompt string

text

    <|system|>
    {system_prompt}</s>
    <|user|>
    {prompt}</s>
    <|assistant|>

—Reverse prompt: </s>

—Context size: 4096

—Run as LlamaEdge service

bash

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:zephyr-7b-alpha-Q5_K_M.gguf llama-api-server.wasm -p zephyr -r '</s>'

—Run as LlamaEdge command app

bash

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:zephyr-7b-alpha-Q5_K_M.gguf llama-chat.wasm -p zephyr -r '</s>'

Prompt Template

text

<|system|>
{system_prompt}</s>
<|user|>
{prompt}</s>
<|assistant|>

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
zephyr-7b-alpha-Q2_K.gguf	Q2_K	2	2.7 GB	smallest, significant quality loss - not recommended for most purposes
zephyr-7b-alpha-Q3_K_L.gguf	Q3KL	3	3.82 GB	small, substantial quality loss
zephyr-7b-alpha-Q3_K_M.gguf	Q3KM	3	3.52 GB	very small, high quality loss
zephyr-7b-alpha-Q3_K_S.gguf	Q3KS	3	3.16 GB	very small, high quality loss
zephyr-7b-alpha-Q4_0.gguf	Q4_0	4	4.11 GB	legacy; small, very high quality loss - prefer using Q3KM
zephyr-7b-alpha-Q4_K_M.gguf	Q4KM	4	4.37 GB	medium, balanced quality - recommended
zephyr-7b-alpha-Q4_K_S.gguf	Q4KS	4	4.14 GB	small, greater quality loss
zephyr-7b-alpha-Q5_0.gguf	Q5_0	5	5.00 GB	legacy; medium, balanced quality - prefer using Q4KM
zephyr-7b-alpha-Q5_K_M.gguf	Q5KM	5	5.13 GB	large, very low quality loss - recommended
zephyr-7b-alpha-Q5_K_S.gguf	Q5KS	5	5.00 GB	large, low quality loss - recommended
zephyr-7b-alpha-Q6_K.gguf	Q6_K	6	5.94 GB	very large, extremely low quality loss
zephyr-7b-alpha-Q8_0.gguf	Q8_0	8	7.70 GB	very large, extremely low quality loss - not recommended