ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_iter_3
huggingface/ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_iter_3
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 59.186%
11 indexed models
11 matching models
huggingface/ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_iter_3
huggingface/ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_4
huggingface/ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4
huggingface/ShenaoZhang/0.001_idpo_iter_1
huggingface/ShenaoZhang/0.001_idpo_iter_2
huggingface/ShenaoZhang/0.001_idpo_iter_3
huggingface/ShenaoZhang/0.001_idpo_noreplacerej_iter_2
huggingface/ShenaoZhang/0.001_idpo_noreplacerej_iter_3
huggingface/ShenaoZhang/0.001_zephyr_5551_4iters_bs256_iter_1
huggingface/ShenaoZhang/0.001_zephyr_5551_4iters_bs256_iter_3
huggingface/ShenaoZhang/0.001_zephyr_5551_4iters_bs256_iter_4
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.