How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kush26/ember"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kush26/ember",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'
Use Docker
docker model run hf.co/Kush26/ember
Quick Links

ember-275m

This model was trained using Forge.

Training Details

  • Final Step: 3650
  • Final Loss: 1.6869081497192382
  • Hardware: modal
  • Orchestration: Nomad Training via Forge

Checkpoint Source

Exported from atomic checkpoint 3650 on the checkpoints branch.

Downloads last month
8
Safetensors
Model size
0.3B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support