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

Libraries

How to use mistralai/Mistral-7B-Instruct-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.1")
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-v0.1")
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1", 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-v0.1 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-v0.1" --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-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mistralai/Mistral-7B-Instruct-v0.1

SGLang

How to use mistralai/Mistral-7B-Instruct-v0.1 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-v0.1" \
    --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-v0.1",
		"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-v0.1" \
        --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-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

How do i get the confidence score of an answer? I want to use this model for question answering task.

#64

by prajwalJumde - opened Oct 30, 2023

Discussion

prajwalJumde

Oct 30, 2023

How do i get the confidence score of an answer? I want to use this model for question answering task.

narai

Nov 2, 2023

If the question is such that the answers are a kind of mutually exclusive multiple choice answer, with a single token answer, then you can get the token probability of the answer. This is available in the API, but not the python API. You can request the top K highest probability tokens and look at the probability of the generated answer token.

narai

Nov 2, 2023

The python API has this in the old openai.Completion interface, which works with some older models only.
response = openai.Completion.create(
model="text-davinci-002",
prompt=prompt,
max_tokens=7,
logprobs=5,
temperature=0
)

narai

Nov 7, 2023

Oops you can ignore my comments about the openai API. You can get the token probabilities for the mistral huggingface output.

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