Instructions to use cloudyu/Mistral-9B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cloudyu/Mistral-9B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="cloudyu/Mistral-9B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cloudyu/Mistral-9B-Instruct")
model = AutoModelForCausalLM.from_pretrained("cloudyu/Mistral-9B-Instruct")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cloudyu/Mistral-9B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cloudyu/Mistral-9B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudyu/Mistral-9B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cloudyu/Mistral-9B-Instruct

SGLang

How to use cloudyu/Mistral-9B-Instruct 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 "cloudyu/Mistral-9B-Instruct" \
    --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": "cloudyu/Mistral-9B-Instruct",
		"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 "cloudyu/Mistral-9B-Instruct" \
        --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": "cloudyu/Mistral-9B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cloudyu/Mistral-9B-Instruct with Docker Model Runner:
```
docker model run hf.co/cloudyu/Mistral-9B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

this a 9B mistral model based on mistralai/Mistral-7B-Instruct-v0.2 and fine-tuned by vicgalle/alpaca-gpt4

it's MMLU is 61.71 , better than 60.78 of mistralai/Mistral-7B-Instruct-v0.2

example output

<s> write me a story about peppa pig. Peppa Pig is a lovable little cartoon character who lives in a house with her family, including her brother George and their mommy and daddy. She enjoys playing outside, going on adventures, and spending time with her friends.
One sunny morning, Peppa woke up early and couldn't wait to start the day. She put on her favorite red dress and went outside to play in the garden. Her brother George was already there, playing with his toy cars.
"Hey, Peppa! Want to race my car with you?" he asked.
Peppa smiled and agreed. They lined up their toys and started racing around the garden. Peppa's car went faster than ever before, but she didn't let that stop her from having fun. When they finished racing, they played hide-and-seek together.
After playing outside for a while, it was time for lunch. Mommy made them some delicious sandwiches, and they all sat down at the table to eat. After lunch, they watched a movie together on the couch.
In the afternoon, Peppa and her family went to visit their friends, the Zebras. They had a great time playing games and eating snacks. When it was time to go home, they said goodbye to their friends and headed back to their own house.
That night, after dinner, Peppa and her family cuddled up on the couch to watch TV together. It had been a wonderful day full of love, laughter, and adventure. And as they drifted off to sleep, they knew that tomorrow would be just as special. The end.</s>

Downloads last month: 9

Safetensors

Model size

9B params

Tensor type

F32

Model tree for cloudyu/Mistral-9B-Instruct

Quantizations

1 model