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.
CON-PPO-TEST2besstie-sarcasm-deberta-v3critic_600_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-1000-f553c1779bppo-reward-model-bertRLHF-PPO-RewardModel-LLama3-3B-v2RLHF-PPO-RewardModel-LLama3-1B-v1RLHF-PPO-RewardModel-LLama3-1B-v1.1pythia_tldr_ppo_1b_valueppo-reward-modelfinetuned-amazon_reviews_multihuggingface_trainQwen-1.5B-Instruct-ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-sub-8cd26db347critic_250_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-500-6394f91930critic_250_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-500-517c4b730fllama-3.2-3b_ppo_lr5e-07_rm_data-mix_no_sys_msg_unfilteredllm-course-hw2-ppocritic_200_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-1000-c08ed8b533besstie-sentiment-deberta-v3critic_800_Qwen-1.5B-Instruct-ppo-run-math-training-prompt-len-800-response-len-4096-0c4e7a4810critic_16_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-5000-0f12cee30ecritic_800_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-1000-3c88380befcritic_450_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-500-26d437d2d8critic_250_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-500-0b10fb3ecbcritic_50_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-500-96479447bbcritic_16_ppo-run-math-training-prompt-len-800-response-len-4096-seed-43-subset-500-a-9a44e3cd58critic_450_ppo-run-math-training-prompt-len-800-response-len-4096-bce-loss-temperatur-9fe16df365critic_1200_ppo-run-math-training-prompt-len-800-response-len-4096-bce-loss-temperatu-6aa1e360d1critic_600_deepseek-r1-distil-1.5b-ppo-run-math-training-prompt-len-800-response-len-07fa1b4078critic_400_ppo-run-math-training-prompt-len-800-response-len-4096-r3-actor-low-lr-0-4bac9e133ellama-3.2-3b_ppo_lr5e-07_rm_avg_w_sys_msg_unfiltered
