Text Generation
Transformers
Safetensors
English
German
mistral
Merge
mergekit
text-generation-inference
Instructions to use malteos/hermeo-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use malteos/hermeo-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="malteos/hermeo-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("malteos/hermeo-7b") model = AutoModelForCausalLM.from_pretrained("malteos/hermeo-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use malteos/hermeo-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "malteos/hermeo-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "malteos/hermeo-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/malteos/hermeo-7b
- SGLang
How to use malteos/hermeo-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 "malteos/hermeo-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": "malteos/hermeo-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 "malteos/hermeo-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": "malteos/hermeo-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use malteos/hermeo-7b with Docker Model Runner:
docker model run hf.co/malteos/hermeo-7b
About mergekit
#2
by OveJie - opened
Your model is quite good. Can you tell me which merge method from mergekit you used? Is it possible to share the specific yml file?
malteos changed discussion status to closed
Perhaps you could also upload the configuration file?