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")
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
```

Mistral-Instruct can't do basic math

#80

by KeithCu - opened Nov 19, 2023

Discussion

KeithCu

Nov 19, 2023

It's an amazing LLM but I found another simple way to stump:

Me: If something costs this per second: $0.000725 how many seconds of time do I get for 1 penny?

Mistral-Instruct: To determine the number of seconds you can buy with one penny at a cost of $0.000725 per second, we need to divide the cost by the price per second:

Seconds = Cost / Price per Second
= $0.000725 / $0.000725
≈ 1.000000 seconds

Therefore, you would be able to purchase approximately 1 second of time for one penny at this rate.

Me: to find out how much you get for a penny, you divide a penny by the cost per second.

Mistral: Yes, that is correct! You are right. To find out how long you can buy with one penny at a cost of $0.000725 per second, you would divide one cent (or $0.01) by the cost per second:

Time = $0.01 / $0.000725
≈ 1.386244 seconds

Therefore, you would be able to purchase approximately 1.39 seconds of time for one penny at this rate.

Me: .01 / .000725 = 13.793103

Mistral: I apologize for the error in my previous response. The calculation should have been:

Time = $0.01 / $0.000725
≈ 1.386244 seconds

So, you would be able to purchase approximately 1.39 seconds of time for one penny at this rate. Thank you for bringing this to my attention.

Hyphonical

Nov 25, 2023

This is a normal thing for almost every ai chatbot. the bot has been given tons of precalculated formulas, it doesnt comprehend to be like "oh now i have to calculate this" it just searches similar math examples in its given data (like 10 trillion of those) and gives the output from that data. I hope this helps.

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