Instructions to use RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit

SGLang

How to use RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit
```

Model Card for Mistral-7B-Instruct-v0.3 quantized to 4bit weights

Weight-only quantization of Mistral-7B-Instruct-v0.3 via GPTQ to 4bits with group_size=128
GPTQ optimized for 99.75% accuracy recovery relative to the unquantized model

Open LLM Leaderboard evaluation scores

	Mistral-7B-Instruct-v0.3	Mistral-7B-Instruct-v0.3-GPTQ-4bit (this model)
arc-c 25-shot	63.48	63.40
mmlu 5-shot	61.13	60.89
hellaswag 10-shot	84.49	84.04
winogrande 5-shot	79.16	79.08
gsm8k 5-shot	43.37	45.41
truthfulqa 0-shot	59.65	57.48
Average Accuracy	65.21	65.05
Recovery	100%	99.75%

vLLM Inference Performance

This model is ready for optimized inference using the Marlin mixed-precision kernels in vLLM: https://github.com/vllm-project/vllm

Simply start this model as an inference server with:

python -m vllm.entrypoints.openai.api_server --model neuralmagic/Mistral-7B-Instruct-v0.3-GPTQ-4bit

Downloads last month: 1,180

Safetensors

Model size

7B params

Tensor type

I32

F16

Model tree for RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Quantized

(266)

this model

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set self-reported

63.400
normalized accuracy on HellaSwag (10-Shot)
validation set self-reported

84.040
mc2 on TruthfulQA (0-shot)
validation set self-reported

57.480
accuracy on GSM8k (5-shot)
test set self-reported

45.410
accuracy on MMLU (5-Shot)
test set self-reported

61.070
accuracy on Winogrande (5-shot)
validation set self-reported

79.080