vwxyzjn on Hugging Face: model downloads
vwxyzjn has 136 tracked models, downloaded 1,832 times in the last 30 days and 71,946 times in total. vwxyzjn Wrapped: the last 12 months.
Models by downloads in the last 30 days
- vwxyzjn/EleutherAI_pythia-1b-deduped__sft__tldr 93 downloads, text generation
- vwxyzjn/reward_modeling__EleutherAI_pythia-14m 78 downloads, model
- vwxyzjn/starcoderbase-triviaqa 47 downloads, text generation
- vwxyzjn/starcoderbase-triviaqa1 42 downloads, text generation
- vwxyzjn/mistral-7b-dpo-constitutional-ai 41 downloads, text generation
- vwxyzjn/starcoderbase_1_0_triviaqa 35 downloads, text generation
- vwxyzjn/rloo_tldr 33 downloads, text generation
- vwxyzjn/EleutherAI_pythia-2.8b-deduped__sft__tldr 30 downloads, text generation
- vwxyzjn/EleutherAI_pythia-6.9b-deduped__sft__tldr 27 downloads, text generation
- vwxyzjn/ppo_tldr 25 downloads, text generation
- vwxyzjn/ppo1 24 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_warmup_1e-6_promising 23 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm 21 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1404__1697168449 21 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_kl_0.33 20 downloads, text generation
- vwxyzjn/ppo_zephyr1 20 downloads, text generation
- vwxyzjn/online_dpo_llmjudge 18 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1__1698542727 18 downloads, text generation
- vwxyzjn/output 18 downloads, text generation
- vwxyzjn/sft 18 downloads, text generation
- vwxyzjn/online_dpo_tldr_6.9b 17 downloads, text generation
- vwxyzjn/rloo_tldr_6.9b 17 downloads, text generation
- vwxyzjn/ppo 17 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1__1697905931 17 downloads, text generation
- vwxyzjn/online_dpo_tulu_2 16 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1301__1697169023 16 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_k4_seed2 16 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_kl_0.32 16 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_warmup_1e-6_larger_bs 16 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1401__1697168334 16 downloads, text generation
- vwxyzjn/train_policy_accelerate__sentiment_offline_5k.json__seed1__1696447674 16 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1302__1697169015 16 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1403__1697168471 16 downloads, text generation
- vwxyzjn/ppo_zephyr9 15 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1__1697905371 15 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_bs64 15 downloads, text generation
- vwxyzjn/ppo_zephyr2 15 downloads, text generation
- vwxyzjn/sft_openassistant-guanaco 15 downloads, text generation
- vwxyzjn/EleutherAI_pythia-6.9b-deduped__reward__tldr 15 downloads, model
- vwxyzjn/ppo_mistral_vllm_1e-6_kl_0.15 15 downloads, text generation
- vwxyzjn/ppo_mistral_vllm_2e-6_kl_0.03 14 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1202__1697170473 14 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_2 14 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_4 14 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1303__1697169064 14 downloads, text generation
- vwxyzjn/ppo_tldr_6.9b_vllm 14 downloads, text generation
- vwxyzjn/ppo_zephyr4 14 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1300__1697169266 14 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1304__1697169024 13 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1203__1697170797 13 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_warmup 13 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_k2_seed1 13 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1201__1697170415 13 downloads, text generation
- vwxyzjn/ppo_mistral_vllm_1e-6_warmup_0.1 13 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1200__1697170464 13 downloads, text generation
- vwxyzjn/ppo_tldr_6.9b 13 downloads, text generation
- vwxyzjn/online_dpo_tldr 13 downloads, text generation
- vwxyzjn/ppo_zephyr310 13 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1400__1697168329 13 downloads, text generation
- vwxyzjn/ppo_mistral_vllm_1e-6_warmup_0.2 13 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1204__1697170542 13 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.03_num_mini_batches_2 12 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_kl_0.23 12 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm11 12 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.02_num_mini_batches_2 12 downloads, text generation
- vwxyzjn/train_sft_accelerate_summarize__tldr__seed1402__1697168345 12 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_warmup_0.2 12 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_warmup_0.4 12 downloads, text generation
- vwxyzjn/EleutherAI_pythia-2.8b-deduped__reward__tldr 11 downloads, model
- vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.15 11 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.02_num_mini_batches_4 11 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_bs128 11 downloads, text generation
- vwxyzjn/online_dpo_debug3 11 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_k4_seed1 11 downloads, text generation
- vwxyzjn/rm_zephyr 11 downloads, text classification
- vwxyzjn/ppo_mistral_vllm_1e-6_1024_2 11 downloads, text generation
- vwxyzjn/ppo_mistral_vllm_1e-6_kl_0.05 11 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.02_num_mini_batches_1 11 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_warmup 11 downloads, text generation
- vwxyzjn/ppo_mistral_vllm_2e-6_kl_0.15 11 downloads, text generation
- vwxyzjn/rm_test 10 downloads, text classification
- vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.02_num_mini_batches_2 10 downloads, text generation
- vwxyzjn/btulu 10 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_rm_norm3 10 downloads, text generation
- vwxyzjn/rm 10 downloads, text classification
- vwxyzjn/rm_1b 10 downloads, text classification
- vwxyzjn/ppo_zephyr7 10 downloads, text generation
- vwxyzjn/ppo_mistral_vllm_1e-6_kl_0.03 10 downloads, text generation
- vwxyzjn/ppo_sync 10 downloads, model
- vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.02_num_mini_batches_1 10 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.03 10 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_test 10 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_kl_0.31 10 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_warmup_2e-6 9 downloads, text generation
- vwxyzjn/ppo_mistral_vllm_2e-6_kl_0.05 9 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_1 9 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_warmup_1e-6_larger_bs_300k_episodes 9 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_warmup_0.3 9 downloads, text generation
- vwxyzjn/ppo_zephyr_vllm_rm_norm 9 downloads, text generation
- vwxyzjn/rloo_zephyr_vllm_k2_seed2 9 downloads, text generation