Gen-Verse / ReasonFlux Star 376 Code Issues Pull requests ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates reinforcement-learning chain-of-thought llm-rlhf sft-data o1-mini o1-preview deepseek-v3 deepseek-r1 Updated Apr 6, 2025 Python
yiyepiaoling0715 / codellm-data-preprocess-pipeline Star 38 Code Issues Pull requests 代码大模型 预训练&微调&DPO 数据处理 业界处理pipeline sota topological-sort fim function-dependency pretrain-data sft-data codellm-completion Updated Jul 25, 2024 Python
open-sciencelab / GraphGen Star 22 Code Issues Pull requests GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation qa knowledge-graph data-generation sft pretrain ai4science llm llm-training qwen xtuner sft-data Updated Apr 22, 2025 Python
Evil-cyber65 / ReasonFlux Star 0 Code Issues Pull requests ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates reinforcement-learning chain-of-thought llm-rlhf sft-data o1-mini o1-preview deepseek-v3 deepseek-r1 Updated Mar 23, 2025