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")
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
```

Mistral-7B-Instruct-v0.2 model reading issue when using Transformer imported from mistral_inference.model

#142

by EnRaoufi - opened Jul 3, 2024

Discussion

EnRaoufi

Jul 3, 2024

I downloaded all the Mistral-7B-Instruct-v0.2 files and tried to use the code snippet given in the Model card to read the model from_folder. I faced this error:

File "/home/user/.local/lib/python3.10/site-packages/mistral_inference/model.py", line 378, in from_folder
    with open(Path(folder) / "params.json", "r") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'mistral_model/mistralai/Mistral-7B-Instruct-v0.2/params.json'

I've found a solution here. After renaming config.json to params.json, I'm encountering this error:

Traceback (most recent call last):
  File "/home/user/.local/lib/python3.10/site-packages/simple_parsing/helpers/serialization/serializable.py", line 893, in from_dict
    instance = cls(**init_args)  # type: ignore
TypeError: ModelArgs.__init__() missing 7 required positional arguments: 'dim', 'n_layers', 'head_dim', 'hidden_dim', 'n_heads', 'n_kv_heads', and 'norm_eps'

My questions are:

How to solve this issue and read the model locally?
How to read the model using Transformer imported from mistral_inference.model without locally saving the model?

Any help would be greatly appreciated.

wwwkun

Jul 6, 2024

me too

EnRaoufi

Jul 15, 2024

@patrickvonplaten @Jacoboooooooo Regarding alignment of encoded vectors achieved by Transformers.AutoTokenizer and MistralTokenizer.v1(), is it still necessary to use Mistral Tokenizer when using the "Mistral-7B-Instruct-v0.2" model to generate texts over a given prompt? If yes, could you please help me with the above issue of using the Mistral Tokenizer?

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