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
```

Process finished with exit code -1073741819 (0xC0000005) on Windows 10 Enterprise and Python 3.11

#27

by roboboot - opened Dec 20, 2023

Discussion

roboboot

Dec 20, 2023

I'm on Windows 10 Enterprise (64 bit - Intel(R) Xeon(R) Gold 6238R CPU @ 2.20GHz) and got the Mistral-7B-Instruct-v0.2.

The running code is the following:

**
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("../Mistral-7B-Instruct-v0.2")
tokenizer = AutoTokenizer.from_pretrained("../Mistral-7B-Instruct-v0.2")
**

Every time I run the code I get the error:

Process finished with exit code -1073741819 (0xC0000005)

Do you have any suggestions?

DeltaLux

Jan 1, 2024

Maybe try this:

from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "../Mistral-7B-Instruct-v0.2"
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cpu")
tokenizer = AutoTokenizer.from_pretrained(model_id)

text = "<s>[INST] What is your favourite condiment? [/INST]"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

I got the same error and what fixed it was specifying the property device_map="cpu" when calling from_pretrained. I also get the same error when I run out of RAM while loading the model as on my machine it consumes about 29 GB of memory. If this code doesn't fix it, check the RAM consumption while it tries to load the model to see if it is that.

roboboot

Jan 2, 2024

Yes, true, it's a memory problem. I have 16 GB of RAM and it's not enough on a Windows machine.

So the model will be entirely loaded in memory....

thx

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