Spaces:

---

smol-course

/

leaderboard

like 7

Running

Eval command:
hf jobs uv run --flavor a10g-large --timeout 3h --with "lighteval[vllm], emoji" --secrets HF_TOKEN lighteval vllm "model_name=pmakiela/SmolLM3-3B-dpo-v0_1" "leaderboard|truthfulqa:mc|0|0,leaderboard|hellaswag|0|0,leaderboard|arc:challenge|0|0" --push-to-hub --results-org pmakiela

Train command:
hf jobs uv run --flavor a100-large --secrets HF_TOKEN --timeout 3h dpo_training.py