Instructions to use bartowski/Hyperion-2.0-Mistral-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/Hyperion-2.0-Mistral-7B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/Hyperion-2.0-Mistral-7B-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/Hyperion-2.0-Mistral-7B-GGUF", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bartowski/Hyperion-2.0-Mistral-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Hyperion-2.0-Mistral-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Hyperion-2.0-Mistral-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF

SGLang

How to use bartowski/Hyperion-2.0-Mistral-7B-GGUF 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 "bartowski/Hyperion-2.0-Mistral-7B-GGUF" \
    --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": "bartowski/Hyperion-2.0-Mistral-7B-GGUF",
		"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 "bartowski/Hyperion-2.0-Mistral-7B-GGUF" \
        --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": "bartowski/Hyperion-2.0-Mistral-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bartowski/Hyperion-2.0-Mistral-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF
```

Llamacpp Quantizations of Hyperion-2.0-Mistral-7B

Using llama.cpp release b2354 for quantization.

Original model: https://huggingface.co/Locutusque/Hyperion-2.0-Mistral-7B

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Description
Hyperion-2.0-Mistral-7B-Q8_0.gguf	Q8_0	7.69GB	Extremely high quality, generally unneeded but max available quant.
Hyperion-2.0-Mistral-7B-Q6_K.gguf	Q6_K	5.94GB	Very high quality, near perfect, recommended.
Hyperion-2.0-Mistral-7B-Q5_K_M.gguf	Q5_K_M	5.13GB	High quality, very usable.
Hyperion-2.0-Mistral-7B-Q5_K_S.gguf	Q5_K_S	4.99GB	High quality, very usable.
Hyperion-2.0-Mistral-7B-Q5_0.gguf	Q5_0	4.99GB	High quality, older format, generally not recommended.
Hyperion-2.0-Mistral-7B-Q4_K_M.gguf	Q4_K_M	4.36GB	Good quality, similar to 4.25 bpw.
Hyperion-2.0-Mistral-7B-Q4_K_S.gguf	Q4_K_S	4.14GB	Slightly lower quality with small space savings.
Hyperion-2.0-Mistral-7B-Q4_0.gguf	Q4_0	4.10GB	Decent quality, older format, generally not recommended.
Hyperion-2.0-Mistral-7B-Q3_K_L.gguf	Q3_K_L	3.82GB	Lower quality but usable, good for low RAM availability.
Hyperion-2.0-Mistral-7B-Q3_K_M.gguf	Q3_K_M	3.51GB	Even lower quality.
Hyperion-2.0-Mistral-7B-Q3_K_S.gguf	Q3_K_S	3.16GB	Low quality, not recommended.
Hyperion-2.0-Mistral-7B-Q2_K.gguf	Q2_K	2.71GB	Extremely low quality, not recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Downloads last month: 67

GGUF

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

bartowski
/

Hyperion-2.0-Mistral-7B-GGUF

Llamacpp Quantizations of Hyperion-2.0-Mistral-7B

Dataset used to train bartowski/Hyperion-2.0-Mistral-7B-GGUF