Instructions to use mistralai/Mistral-7B-Instruct-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mistralai/Mistral-7B-Instruct-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mistralai/Mistral-7B-Instruct-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Install mistral-common:
pip install --upgrade mistral-common
# Start the vLLM server:
vllm serve "mistralai/Mistral-7B-Instruct-v0.2" --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mistralai/Mistral-7B-Instruct-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mistralai/Mistral-7B-Instruct-v0.2

SGLang

How to use mistralai/Mistral-7B-Instruct-v0.2 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 "mistralai/Mistral-7B-Instruct-v0.2" \
    --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": "mistralai/Mistral-7B-Instruct-v0.2",
		"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 "mistralai/Mistral-7B-Instruct-v0.2" \
        --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": "mistralai/Mistral-7B-Instruct-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mistralai/Mistral-7B-Instruct-v0.2 with Docker Model Runner:
```
docker model run hf.co/mistralai/Mistral-7B-Instruct-v0.2
```

Tryint to use private-gpt with Mistral but not having access to model

#127

by hitoruna - opened May 20, 2024

Discussion

hitoruna

May 20, 2024

I am trying to use private-gpt (https://docs.privategpt.dev/installation/getting-started/installation#local-ollama-powered-setup---recommended) which uses mistral but when I do PGPT_PROFILES=ollama make run I get

You are trying to access a gated repo.
Make sure to have access to it at https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2.
401 Client Error. (Request ID: Root=1-664ac2d9-648ebce1202a3b494633c746;52185420-fabc-421f-9fb9-627f32bfac6a)

Cannot access gated repo for url https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2/resolve/main/config.json.
Access to model mistralai/Mistral-7B-Instruct-v0.2 is restricted. You must be authenticated to access it.

I have already done what is suggested in here with generating an access token and doing
poetry run huggingface-cli login --token

and I got

Token will not been saved to git credential helper. Pass add_to_git_credential=True if you want to set the git credential as well.
Token is valid (permission: read).
Your token has been saved to /home/user/.cache/huggingface/token
Login successful

Still the error is happening.
How can this be solved?

hitoruna changed discussion title from Tryint to use private-gpt with Mistral to Tryint to use private-gpt with Mistral but not havving access to model May 20, 2024

hitoruna changed discussion title from Tryint to use private-gpt with Mistral but not havving access to model to Tryint to use private-gpt with Mistral but not having access to model May 20, 2024

jayoon16

May 23, 2024

Same... HELP

hitoruna

May 23, 2024

•

edited May 23, 2024

Get a token here
in your environment set export HUGGINGFACE_TOKEN=your token
export HUGGINGFACE_API_KEY=your token
Run huggingface-cli login --token your token
After that you have access to the resource

The question is why do I need this for... I dont know...
Hope it helps

KaityTT

Jun 11, 2024

•

edited Jun 11, 2024

Why we can't simple download it and use it in the local machine? If is possible, why not create an example loading it from the disk? That is my next step. Going to try to do it. Wish me luck.
Actually. I really would like a tutorial of how can I expand it and train it myself. I'm looking around the site for a few hours now and I simply can't find examples.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment