Instructions to use dmitrybright/Mistral-7B-Instruct-v0.1-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dmitrybright/Mistral-7B-Instruct-v0.1-8bit with Transformers:

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

pipe = pipeline("text-generation", model="dmitrybright/Mistral-7B-Instruct-v0.1-8bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dmitrybright/Mistral-7B-Instruct-v0.1-8bit")
model = AutoModelForCausalLM.from_pretrained("dmitrybright/Mistral-7B-Instruct-v0.1-8bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dmitrybright/Mistral-7B-Instruct-v0.1-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dmitrybright/Mistral-7B-Instruct-v0.1-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dmitrybright/Mistral-7B-Instruct-v0.1-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dmitrybright/Mistral-7B-Instruct-v0.1-8bit

SGLang

How to use dmitrybright/Mistral-7B-Instruct-v0.1-8bit 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 "dmitrybright/Mistral-7B-Instruct-v0.1-8bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dmitrybright/Mistral-7B-Instruct-v0.1-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "dmitrybright/Mistral-7B-Instruct-v0.1-8bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dmitrybright/Mistral-7B-Instruct-v0.1-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dmitrybright/Mistral-7B-Instruct-v0.1-8bit with Docker Model Runner:
```
docker model run hf.co/dmitrybright/Mistral-7B-Instruct-v0.1-8bit
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Mistral-7B-Instruct-v0.1-8bit

Create model

model_path = "mistralai/Mistral-7B-Instruct-v0.1"
bnb_config = BitsAndBytesConfig(
    load_in_8bit=True
)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, quantization_config=bnb_config, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_path)

Load in pipeline

text_generation_pipeline = transformers.pipeline(
    model=model,
    tokenizer=tokenizer,
    task="text-generation",
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.eos_token_id,
    repetition_penalty=1.1,
    return_full_text=True,
    max_new_tokens=100,
)
mistral_llm = HuggingFacePipeline(pipeline=text_generation_pipeline)

text = "what is mistral?"
mistral_llm.invoke(text)

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

F32

F16