tyler-romero / microR1Links
Simple repository for training small reasoning models
☆37Updated 6 months ago
Alternatives and similar repositories for microR1
Users that are interested in microR1 are comparing it to the libraries listed below
Sorting:
- Simple GRPO scripts and configurations.☆59Updated 6 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆97Updated 3 weeks ago
- LLM training in simple, raw C/CUDA☆15Updated 8 months ago
- ☆54Updated 9 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- Verifiers for LLM Reinforcement Learning☆70Updated 4 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆69Updated 4 months ago
- ☆48Updated 11 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆68Updated 4 months ago
- Train your own SOTA deductive reasoning model☆104Updated 5 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 5 months ago
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆33Updated 4 months ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆51Updated 4 months ago
- ☆27Updated last year
- ☆39Updated last year
- ☆85Updated last year
- Compiling useful links, papers, benchmarks, ideas, etc.☆45Updated 5 months ago
- Storing long contexts in tiny caches with self-study☆140Updated this week
- rl from zero pretrain, can it be done? yes.☆257Updated this week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 7 months ago
- Collection of autoregressive model implementation☆86Updated 4 months ago
- ☆120Updated 6 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆95Updated last month
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆25Updated 2 months ago
- Official Repo for InSTA: Towards Internet-Scale Training For Agents☆54Updated last month
- ☆58Updated 3 months ago
- ☆26Updated 7 months ago
- ☆61Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 2 weeks ago