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.
BARC-1B-RL-training-v2-check-GGUFrlcr-readout-qwen3.5-4b-training-basegpt2-last_token_reward_and_full_training-rlhf-rm-checkpointgpt2-training-full-rlhf-rm-checkpointqwen3-8b-combined-sft-training-data-v20250824_MiroSystemPromptqwen3-4b-it-combined-sft-training-data-v20250824_MiroSystemPromptqwen3-8b-base-combined-sft-training-data-v20250824_MiroSystemPromptqwen2.5-7b-combined-sft-training-data-v20250824_MiroSystemPromptrl_training_output_8xh100_b2g2
