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.
FC-VERL-JSON-1.5B-GGUFptdbench-verl-implementation-torch-functionalptdbench-verl-coding-task-evaluatorptdbench-verl-coding-tasks-function-callverl-grpo-medium-qwen3-4b-step129-reprodistilbert-base-uncased-finetuned-colaverl-grpo-medium-qwen3-4b-step129verl-grpo-medium-qwen3-4b-step100verl-grpo-medium-qwen3-4b-step50verl-grpo-medium-qwen3-4b-step50-reproverl-grpo-medium-qwen3-4b-step100-reproMegaSW_verl_sft-GGUFQwen2.5-Coder-7B-TIR-SFT-new-Interpreter-Thinkingmini-verl-qwen3-1.7b-protocol-teacherqwen-abs-verl-sft-rephrased-lr5e6-ep1-0109DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1llama-3.2-3b-gsm8k-ppo-verl-step6verl-math-transfer-7bi-to-7bi-v2verl-math-transfer-7bi-to-3bi-fix03qwen2.5-1.5b-verl-python-mergedllama-3.2-3b-gsm8k-ppo-verl-step8llama-3.2-3b-gsm8k-ppo-verl-step48FC-VERL-JSON-1.5Bfc-rag-sft-verlverl-math-transfer-7bi-to-3bi-fix07-pool7to1verl-math-transfer-7bi-to-3bi-fix05-pool7to1Hinglish-Bert-Classllama-3.2-3b-gsm8k-ppo-verl-step20verl_grpo_05B