Instructions to use ariG23498/Mistral-7B-Instruct-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ariG23498/Mistral-7B-Instruct-v0.3 with Transformers:

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

pipe = pipeline("text-generation", model="ariG23498/Mistral-7B-Instruct-v0.3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ariG23498/Mistral-7B-Instruct-v0.3")
model = AutoModelForCausalLM.from_pretrained("ariG23498/Mistral-7B-Instruct-v0.3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ariG23498/Mistral-7B-Instruct-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ariG23498/Mistral-7B-Instruct-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ariG23498/Mistral-7B-Instruct-v0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ariG23498/Mistral-7B-Instruct-v0.3

SGLang

How to use ariG23498/Mistral-7B-Instruct-v0.3 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 "ariG23498/Mistral-7B-Instruct-v0.3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ariG23498/Mistral-7B-Instruct-v0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ariG23498/Mistral-7B-Instruct-v0.3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ariG23498/Mistral-7B-Instruct-v0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ariG23498/Mistral-7B-Instruct-v0.3 with Docker Model Runner:
```
docker model run hf.co/ariG23498/Mistral-7B-Instruct-v0.3
```

Turns out that Mistral-7B-Instruct-v0.3 only have safetensors. This repo is created to have the .bin files of the model.

This repo is created by:

model_id = "mistralai/Mistral-7B-Instruct-v0.3"
model = AutoModelForCausalLM.from_pretrained(model_id)
model.push_to_hub("ariG23498/Mistral-7B-Instruct-v0.3", safe_serialization=False)

This is due to the fact that the TensorFlow port cannot use safetensors and need bin files.

You can use this model with TF like so:

model_tf = TFAutoModelForCausalLM.from_pretrained("ariG23498/Mistral-7B-Instruct-v0.3", from_pt=True)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")

prompt = "My favourite condiment is"
model_inputs = tokenizer([prompt], return_tensors="tf")
generated_ids = model_tf.generate(**model_inputs, max_new_tokens=100, do_sample=True)
tokenizer.batch_decode(generated_ids)[0]

As soon as the safetensors and TensorFlow issue is sorted one can ditch this repository and use the official repository!

Update:

I have uploaded the .h5 models as well. You can now use the following and make the entire code work!

model_tf = TFAutoModelForCausalLM.from_pretrained("ariG23498/Mistral-7B-Instruct-v0.3")

Downloads last month: 16

Model tree for ariG23498/Mistral-7B-Instruct-v0.3

Unable to build the model tree, the base model loops to the model itself. Learn more.