DatPySci/pythia-1b-dpo
huggingface/DatPySci/pythia-1b-dpo
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 32.755%
7 indexed models
7 matching models
huggingface/DatPySci/pythia-1b-dpo
huggingface/DatPySci/pythia-1b-dpo-full
huggingface/DatPySci/pythia-1b-kto-iter0
huggingface/DatPySci/pythia-1b-self-kto-iter0
huggingface/DatPySci/pythia-1b-sft-50k
huggingface/DatPySci/pythia-1b-sft-full
huggingface/DatPySci/pythia-1b-spin-iter1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.