models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
grpo_Qwen3-1.7B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30paper-adaptive-clip-1.5bQwen3-14B-Multilingual-GSPO-Clipping-lora-step-140grpo-5e-6_kl_64_clip_higher_binary-step-30Qwen3-14B-Multilingual-GSPO-Clipping-lora-step-200grpo_DeepSeek-R1-Distill-Llama-8B_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30Qwen3-14B-Multilingual-GSPO-Clipping-lora-step-80rpp_dv_clipcov_tok-mean-md-checkpoint_103CHIVA_FINETUNED_QWEN_MODEL_CLIP_DATA_AND_NLP_DATArpp_t_clipcov_llr_new-checkpoint_223grpo_Qwen3-0.6B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30rpp_t_clipcov_llr_new-checkpoint_191rpp_t_clipcov_llr_new-checkpoint_247rpp_dv_clipcov-checkpoint_367_1grpo_Qwen3-4B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30clip-vitb16-qwen2vl-reranker-v2qwen3-0.6b-gsm8k-opsd-fkl-r16-clip005-s800clip-qwen2vl-reranker-v1rpp_t_clipcov_llr_new-checkpoint_271grpo_Qwen3-4B-Instruct-2507_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
