nyu-dice-lab/Mistral-7B-Base-SFT-WildChat
Updated
•
3
WildChat-50m Models
All model checkpoints associated with the WildChat-50m paper, including Re-Wild, DPO, and TULU3.
-
-
nyu-dice-lab/tulu3-dpo-repro
Updated • 14 -
nyu-dice-lab/dpo-q2572b-a70b-jllm3-Factuality-A
Updated • 7 -
nyu-dice-lab/dpo-q2572b-a70b-jllm3-Readability-A
Updated • 9 -
nyu-dice-lab/rewild_sft_tulu_dpo_8b
Updated • 9 -
nyu-dice-lab/dpo-rewild-8b-v0.04
Updated • 8 -
nyu-dice-lab/dpo-rewild-8b-v0.02
Updated • 5 -
nyu-dice-lab/dpo-rewild-8b-v0.03
Updated • 7 -
nyu-dice-lab/dpo-q2572b-a70b-jllm3-Harmlessness-A
Updated • 1 -
nyu-dice-lab/dpo-rewild-8b-v0.05
Updated • 8 -
nyu-dice-lab/dpo-rewild-8b-v0.06
Updated • 5