Inferless/SOLAR-10.7B-Instruct-v1.0-GPTQ

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

Join Private Beta

Go through this tutorial, for quickly deploy SOLAR-10.7B-Instruct-v1.0 using Inferless

---

SOLAR-10.7B-Instruct-v1.0 - GPTQ

• Model creator: Upstage
• Original model: SOLAR-10.7B-Instruct-v1.0

Description

This repo contains GPTQ model files for Upstage's SOLAR-10.7B-Instruct-v1.0.

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:

• Text Generation Webui - using Loader: AutoAWQ
• vLLM - version 0.2.2 or later for support for all model types.
• Hugging Face Text Generation Inference (TGI)
• Transformers version 4.35.0 and later, from any code or client that supports Transformers
• AutoAWQ - for use from Python code

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"

Here is the code for app.py

from vllm import LLM, SamplingParams

class InferlessPythonModel:
    def initialize(self):

        self.sampling_params = SamplingParams(temperature=0.7, top_p=0.95,max_tokens=256)
        self.llm = LLM(model="Inferless/SOLAR-10.7B-Instruct-v1.0-GPTQ", quantization="gptq", dtype="float16")

    def infer(self, inputs):
        prompts = inputs["prompt"]
        result = self.llm.generate(prompts, self.sampling_params)
        result_output = [[[output.outputs[0].text,output.outputs[0].token_ids] for output in result]

        return {'generated_result': result_output[0]}

    def finalize(self):
        pass