Instructions to use axiomepic/harmon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use axiomepic/harmon with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="axiomepic/harmon")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("axiomepic/harmon") model = AutoModelForCausalLM.from_pretrained("axiomepic/harmon") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use axiomepic/harmon with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "axiomepic/harmon" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "axiomepic/harmon", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/axiomepic/harmon
- SGLang
How to use axiomepic/harmon 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 "axiomepic/harmon" \ --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": "axiomepic/harmon", "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 "axiomepic/harmon" \ --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": "axiomepic/harmon", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use axiomepic/harmon with Docker Model Runner:
docker model run hf.co/axiomepic/harmon
Commit ·
e181dae
1
Parent(s): 0988866
Adding `safetensors` variant of this model (#1)
Browse files- Adding `safetensors` variant of this model (374dbb1fd55c8b3aab2c67977ac0b5fa64462de4)
Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>
- model.safetensors +3 -0
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b01d8cc2e48d4f3ba02b227f00e1caa74bea47383502dbaef69f32b42e907e8
|
| 3 |
+
size 344174208
|