tyler-romero / microR1Links
Simple repository for training small reasoning models
☆47Updated 10 months ago
Alternatives and similar repositories for microR1
Users that are interested in microR1 are comparing it to the libraries listed below
Sorting:
- LLM training in simple, raw C/CUDA☆15Updated last year
- ☆48Updated last year
- A collection of lightweight interpretability scripts to understand how LLMs think☆71Updated last week
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆31Updated 6 months ago
- Simple GRPO scripts and configurations.☆59Updated 10 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 2 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆122Updated 2 months ago
- ☆55Updated last year
- Collection of autoregressive model implementation☆85Updated 8 months ago
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- A repository for research on medium sized language models.☆77Updated last year
- Supercharge huggingface transformers with model parallelism.☆77Updated 5 months ago
- ☆91Updated last year
- ☆40Updated last year
- GoldFinch and other hybrid transformer components☆45Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 8 months ago
- ☆59Updated last month
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year
- ☆39Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆86Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 3 months ago
- ☆86Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆76Updated last year
- ☆28Updated last year
- Jax like function transformation engine but micro, microjax☆34Updated last year
- Compiling useful links, papers, benchmarks, ideas, etc.☆45Updated 9 months ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆32Updated 6 months ago
- DPO, but faster 🚀☆46Updated last year
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆63Updated 7 months ago
- Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval☆51Updated last year