Phi 1.5 trained on https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3 for 9 epochs, native finetune.
Prompt format is vicuna style (no system prompt).
USER: <prompt>
ASSISTANT:
- Downloads last month
- 3
Inference API (serverless) does not yet support model repos that contain custom code.