facebookresearch / RAMLinks
A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
☆248Updated last week
Alternatives and similar repositories for RAM
Users that are interested in RAM are comparing it to the libraries listed below
Sorting:
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆208Updated last month
- SkyRL-v0: Train Real-World Long-Horizon Agents via Reinforcement Learning☆375Updated this week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆367Updated last week
- Tina: Tiny Reasoning Models via LoRA☆252Updated last week
- ☆93Updated 8 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆203Updated last year
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"☆155Updated this week
- Code for the paper: "Learning to Reason without External Rewards"☆237Updated this week
- official repository for “Reinforcement Learning for Reasoning in Large Language Models with One Training Example”☆257Updated this week
- Reproducible, flexible LLM evaluations☆204Updated 3 weeks ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆186Updated 3 months ago
- Scalable toolkit for efficient model reinforcement☆385Updated this week
- Complex Function Calling Benchmark.☆112Updated 4 months ago
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"☆144Updated 2 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆333Updated 5 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains☆126Updated last week
- Async pipelined version of Verl☆91Updated last month
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆228Updated 9 months ago
- A project to improve skills of large language models☆415Updated this week
- ☆295Updated last week
- Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆96Updated last month
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆180Updated 2 months ago
- ☆174Updated last month
- PyTorch building blocks for the OLMo ecosystem☆227Updated this week
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆173Updated 3 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆167Updated this week
- LOFT: A 1 Million+ Token Long-Context Benchmark☆198Updated last month
- ☆114Updated 3 months ago
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆239Updated last month
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆215Updated 3 weeks ago