hamishivi / EasyLMLinks
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
☆75Updated 9 months ago
Alternatives and similar repositories for EasyLM
Users that are interested in EasyLM are comparing it to the libraries listed below
Sorting:
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆30Updated 11 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆53Updated last month
- ☆38Updated last year
- ☆120Updated 8 months ago
- ☆79Updated 6 months ago
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆54Updated last year
- ☆97Updated 11 months ago
- Revisiting Mid-training in the Era of RL Scaling☆42Updated last month
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆50Updated last month
- ☆114Updated 3 months ago
- Scalable Meta-Evaluation of LLMs as Evaluators☆42Updated last year
- ☆72Updated last year
- ☆29Updated 10 months ago
- ☆49Updated 2 weeks ago
- ☆44Updated 9 months ago
- ☆113Updated 4 months ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆55Updated 3 months ago
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆29Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆47Updated last year
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆46Updated last year
- A repository for transformer critique learning and generation☆89Updated last year
- Code for Zero-Shot Tokenizer Transfer☆128Updated 4 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆159Updated last week
- Critique-out-Loud Reward Models☆66Updated 7 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆42Updated 6 months ago
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging☆106Updated last year
- Replicating O1 inference-time scaling laws☆87Updated 6 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆106Updated last year
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆201Updated 3 weeks ago