promotion on Hugging Face: model downloads
promotion has 79 tracked models, downloaded 16,797 times in the last 30 days and 17,356 times in total. promotion Wrapped: the last 12 months.
Models by downloads in the last 30 days
- promotion/Llama-3.1-8B-NBPO-finitepool 838 downloads, text generation
- promotion/UW1-SPPO 793 downloads, text generation
- promotion/UW1-INPO-soft 729 downloads, text generation
- promotion/UW1-DPO-soft 729 downloads, text generation
- promotion/UW1-FixedRefNash-PW 723 downloads, text generation
- promotion/UW1-NBPO-PW 709 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-MaxMinRLHF-baseline 585 downloads, text generation
- promotion/Llama-3.1-8B-MaxMinRLHF-baseline 565 downloads, text generation
- promotion/FixedRefNash-Qwen2.5-7B-WildChecklists-2ep 451 downloads, text generation
- promotion/NBPO-Qwen2.5-7B-WildChecklists-2ep 450 downloads, text generation
- promotion/PROSPER-Qwen2.5-7B-WildChecklists-2ep 449 downloads, text generation
- promotion/UW1-PROSPER 392 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-Utilitarian-baseline 378 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-NBPO-600updates 377 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-NBPO-finitepool 374 downloads, text generation
- promotion/Llama-3.1-8B-NBPO-UltraFeedback-600updates 370 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-SurplusMaxMin-baseline 361 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-AbsoluteMaxMin-baseline 351 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-NBPO-stage2 351 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-NBPO-600updates 350 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-Panacea-baseline 347 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-NBPO-finitepool 344 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-RewardedSoups-baseline 344 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-RewardedSoups-baseline 343 downloads, text generation
- promotion/Llama-3.1-8B-SurplusMaxmin-baseline 341 downloads, text generation
- promotion/Llama-3.1-8B-Panacea-baseline 339 downloads, text generation
- promotion/Llama-3.1-8B-AbsoluteMaxmin-baseline 337 downloads, text generation
- promotion/Llama-3.1-8B-FixedReferenceNBPO 309 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-Utilitarian-baseline 303 downloads, text generation
- promotion/Llama-3.1-8B-RewardedSoups-baseline 303 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-MaxMinRLHF-baseline 298 downloads, text generation
- promotion/Llama-3.1-8B-NBPO-UltraFeedback-clean 293 downloads, text generation
- promotion/Qwen3-8B-Panacea-baseline 292 downloads, text generation
- promotion/Llama-3.1-8B-NBPO-UltraFeedback-eta0.05 292 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-AbsoluteMaxMin-baseline 290 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-NBPO-eta0.1 287 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-SurplusMaxMin-baseline 287 downloads, text generation
- promotion/Qwen3-8B-RewardedSoups-baseline 287 downloads, text generation
- promotion/Llama-3.1-8B-TLDR-NBPO-eta0.05 285 downloads, text generation
- promotion/Qwen3-8B-MaxMinRLHF-baseline 271 downloads, text generation
- promotion/Llama-3.1-8B-SafeRLHF-HTMNPO-helpfulness 12 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-Utilitarian 12 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-HTMNPO-harmlessness 11 downloads, model
- promotion/adarollgrpo-colota-gemma-3-4b-it-sum-sum-sq-a-adaroll-b200 10 downloads, model
- promotion/Llama-3.1-8B-MOPO-baseline 10 downloads, model
- promotion/Llama-3.1-8B-TLDR-Utilitarian 9 downloads, model
- promotion/Llama-3.1-8B-TLDR-MOPO 9 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-PROSPER 9 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-NBPO 9 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-SurplusMaxmin 9 downloads, model
- promotion/Llama-3.1-8B-TLDR-HTMNPO-faithfulness 9 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-AbsoluteMaxmin-beta1.0 8 downloads, model
- promotion/Llama-3.1-8B-TLDR-HTMNPO-helpfulness 8 downloads, model
- promotion/Llama-3.1-8B-TLDR-AbsoluteMaxmin 8 downloads, model
- promotion/adarollgrpo-logiqa-gemma-3-4b-it-sum-max-r-adaroll-b200 8 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-NBPO-beta0.5 8 downloads, model
- promotion/Llama-3.1-8B-TLDR-NBPO 8 downloads, model
- promotion/Llama-3.1-8B-TLDR-SurplusMaxmin 8 downloads, model
- promotion/Llama-3.1-8B-Utilitarian-baseline 8 downloads, model
- promotion/adarollgrpo-logiqa-gemma-3-4b-it-min-max-r-adaroll-b200 7 downloads, model
- promotion/Qwen3-8B-HTMNPO-instruction-following 7 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-MOPO 7 downloads, model
- promotion/Llama-3.1-8B-TLDR-UniformINPO 7 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-AbsoluteMaxmin-beta0.5 7 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-UniformINPO 7 downloads, model
- promotion/Llama-3.1-8B-TLDR-HTMNPO-conciseness 7 downloads, model
- promotion/adarollgrpo-gemma-3-4b-it-min-sum-sq-a-adaroll-ronpo-b200 6 downloads, model
- promotion/Llama-3.1-8B-SafeRLHF-AbsoluteMaxmin 6 downloads, model
- promotion/adarollgrpo-gemma-3-4b-it-sum-sum-sq-a-adaroll-ronpo-b200 5 downloads, model
- promotion/adarollgrpo-logiqa-gemma-3-4b-it-min-v-adaroll-lr5e-6-b200 5 downloads, model
- promotion/Llama-3.1-8B-TLDR-PROSPER 5 downloads, model
- promotion/adarollgrpo-colota-gemma-3-4b-it-sum-max-r-adaroll-b200 5 downloads, model
- promotion/adarollgrpo-colota-gemma-3-4b-it-min-sum-sq-a-adaroll-b200 4 downloads, model
- promotion/adarollgrpo-colota-gemma-3-4b-it-min-max-r-adaroll-b200 4 downloads, model
- promotion/adarollgrpo-colota-gemma-3-4b-it-sum-v-adaroll-b200 4 downloads, model
- promotion/adarollgrpo-logiqa-gemma-3-4b-it-min-v-adaroll-lr1e-5-b200 4 downloads, model
- promotion/Llama-3.1-8B-TLDR-HTMNPO-coverage 4 downloads, model
- promotion/adarollgrpo-logiqa-gemma-3-4b-it-min-v-adaroll-lr1e-6-b200 3 downloads, model
- promotion/adarollgrpo-logiqa-gemma-3-4b-it-min-v-adaroll-lr5e-5-b200 3 downloads, model