dhcode-cpp / grpo-lossLinks
☆39Updated 10 months ago
Alternatives and similar repositories for grpo-loss
Users that are interested in grpo-loss are comparing it to the libraries listed below
Sorting:
- ☆87Updated 4 months ago
- This is a repo for showcasing using MCTS with LLMs to solve gsm8k problems☆94Updated last month
- Scaling Preference Data Curation via Human-AI Synergy☆135Updated 6 months ago
- RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.☆76Updated 10 months ago
- ☆50Updated last year
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆155Updated last year
- ☆65Updated last year
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆32Updated last year
- Fantastic Data Engineering for Large Language Models☆93Updated last year
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆222Updated 5 months ago
- ☆161Updated 11 months ago
- ☆54Updated last year
- Official completion of “Training on the Benchmark Is Not All You Need”.☆38Updated last year
- ☆124Updated last year
- ☆147Updated last year
- PSFT is a trust-region–inspired fine-tuning objective that views SFT as a policy gradient method with constant advantages, constraining p…☆34Updated 4 months ago
- Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework☆163Updated 3 weeks ago
- ☆130Updated last year
- Pretrain、decay、SFT a CodeLLM from scratch 🧙♂️☆39Updated last year
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆58Updated last year
- Train your grpo with zero dataset and low resources, 8bit/4bit/lora/qlora supported, multi-gpu supported ...☆79Updated 8 months ago
- ☆83Updated last year
- ☆77Updated 11 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated 2 years ago
- Hammer: Robust Function-Calling for On-Device Language Models via Function Masking☆106Updated 6 months ago
- 本项目用于大模型数学解题能力方面的数据集合成,模型训练及评测,相关文章记录。☆99Updated last year
- SuperCLUE-Math6:新一代中文原生多轮多步数学推理数据集的探索之旅☆60Updated last year
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 9 months ago
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆278Updated 10 months ago
- Llama-3-SynE: A Significantly Enhanced Version of Llama-3 with Advanced Scientific Reasoning and Chinese Language Capabilities | 继续预训练提升 …☆36Updated 7 months ago