Instructions to use Locutusque/Hyperion-2.1-Mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/Hyperion-2.1-Mistral-7B with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/Hyperion-2.1-Mistral-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/Hyperion-2.1-Mistral-7B")
model = AutoModelForCausalLM.from_pretrained("Locutusque/Hyperion-2.1-Mistral-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Locutusque/Hyperion-2.1-Mistral-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/Hyperion-2.1-Mistral-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/Hyperion-2.1-Mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/Hyperion-2.1-Mistral-7B

SGLang

How to use Locutusque/Hyperion-2.1-Mistral-7B 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 "Locutusque/Hyperion-2.1-Mistral-7B" \
    --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": "Locutusque/Hyperion-2.1-Mistral-7B",
		"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 "Locutusque/Hyperion-2.1-Mistral-7B" \
        --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": "Locutusque/Hyperion-2.1-Mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/Hyperion-2.1-Mistral-7B with Docker Model Runner:
```
docker model run hf.co/Locutusque/Hyperion-2.1-Mistral-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Description

Further fine-tuned Locutusque/Hyperion-2.0-Mistral-7B at a higher learning rate. This was done to see if performance increased. Read Locutusque/Hyperion-2.0-Mistral-7B's model card for more information. Slight performance gain was observed. More checkpoints will be released in the future.

Disclaimer

This model is very compliant. It will respond to any request without refusal. If you intend to deploy this model at an enterprise level, I would recommend aligning this model using DPO.