rbgo's picture
Update README.md
ece2623 verified
metadata
base_model: mistralai/Mixtral-8x7B-v0.1
inference: false
language:
  - en
license: apache-2.0
model-index:
  - name: Mixtral-8x7B
    results: []
model_creator: mistralai
model_name: Mixtral-8x7B
model_type: mixtral
prompt_template: |
  <|im_start|>system
  {system_message}<|im_end|>
  <|im_start|>user
  {prompt}<|im_end|>
  <|im_start|>assistant
quantized_by: Inferless
tags:
  - mixtral
  - vllm
  - GPTQ
Inferless

Serverless GPUs to scale your machine learning inference without any hassle of managing servers, deploy complicated and custom models with ease.

Go through this tutorial, for quickly deploy Mixtral-8x7B-v0.1 using Inferless


Mixtral-8x7B - GPTQ

Description

This repo contains GPTQ model files for Mistralai's Mixtral-8x7B-v0.1.

About GPTQ

GPTQ is a method that compresses the model size and accelerates inference by quantizing weights based on a calibration dataset, aiming to minimize mean squared error in a single post-quantization step. GPTQ achieves both memory efficiency and faster inference.

It is supported by:

Shared files, and GPTQ parameters

Models are released as sharded safetensors files.

Branch Bits GS AWQ Dataset Seq Len Size
main 4 128 VMware Open Instruct 4096 5.96 GB

How to use

You will need the following software packages and python libraries:

build:
  cuda_version: "12.1.1"
  system_packages:
    - "libssl-dev"
  python_packages:
    - "torch==2.1.2"
    - "vllm==0.2.6"
    - "transformers==4.36.2"
    - "accelerate==0.25.0"