facebookresearch / RAM
A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
β209Updated this week
Alternatives and similar repositories for RAM:
Users that are interested in RAM are comparing it to the libraries listed below
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)β206Updated 10 months ago
- A project to improve skills of large language modelsβ256Updated this week
- πΎ OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.β224Updated 2 weeks ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"β166Updated 2 weeks ago
- The official repo for "LLoCo: Learning Long Contexts Offline"β116Updated 9 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.β164Updated 2 weeks ago
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".β196Updated this week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsβ¦β307Updated 3 months ago
- PyTorch building blocks for the OLMo ecosystemβ165Updated this week
- This is the official repository for Inheritune.β109Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersβ125Updated 3 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"β154Updated 9 months ago
- β103Updated 2 months ago
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"β298Updated last year
- β87Updated 5 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasksβ140Updated 6 months ago
- "Improving Mathematical Reasoning with Process Supervision" by OPENAIβ108Updated 2 weeks ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.β168Updated 2 months ago
- Implementation of π₯₯ Coconut, Chain of Continuous Thought, in Pytorchβ160Updated 2 months ago
- FuseAI Projectβ84Updated last month
- Repo of paper "Free Process Rewards without Process Labels"β136Updated last week
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]β130Updated 6 months ago
- Repository for the paper Stream of Search: Learning to Search in Languageβ142Updated last month
- Reproducible, flexible LLM evaluationsβ176Updated 3 months ago