metadata

license: apache-2.0
library_name: vllm
pipeline_tag: image-text-to-text
tags:
  - int4
  - vllm
  - llmcompressor
base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503

Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g

Model Overview

This model was obtained by quantizing the weights of Mistral-Small-3.1-24B-Instruct-2503 to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.

Only the weights of the linear operators within language_model transformers blocks are quantized. Vision model and multimodal projection are kept in original precision. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization.

Model checkpoint is saved in compressed_tensors format.

Usage

To use the model in transformers update the package to stable release of Mistral-3

pip install git+https://github.com/huggingface/[email protected]
To use the model in vLLM update the package to version vllm>=0.8.0.

And example of inference via transformers is provided below:

# pip install accelerate

from transformers import AutoProcessor, AutoModelForImageTextToText
from PIL import Image
import requests
import torch

model_id = "ISTA-DASLab/Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g"

model = AutoModelForImageTextToText.from_pretrained(
    model_id, device_map="auto"
).eval()

processor = AutoProcessor.from_pretrained(model_id)

messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Describe this image in detail."}
        ]
    }
]

inputs = processor.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=True,
    return_dict=True, return_tensors="pt"
).to(model.device, dtype=torch.bfloat16)

input_len = inputs["input_ids"].shape[-1]

with torch.inference_mode():
    generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
    generation = generation[0][input_len:]

decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)