neilrathi / token-filteringLinks
Shaping capabilities with token-level pretraining data filtering
☆51Updated last week
Alternatives and similar repositories for token-filtering
Users that are interested in token-filtering are comparing it to the libraries listed below
Sorting:
- ☆91Updated last year
- ☆53Updated 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…☆78Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- ☆39Updated 9 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆88Updated last year
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆32Updated 7 months ago
- ☆19Updated 2 months ago
- ☆23Updated last year
- ☆53Updated 2 years ago
- Language models scale reliably with over-training and on downstream tasks☆99Updated last year
- ☆92Updated last year
- ☆53Updated 2 years ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Official repo for Learning to Reason for Long-Form Story Generation☆74Updated 9 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆83Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆84Updated 8 months ago
- Sparse Autoencoder Training Library☆56Updated 9 months ago
- A toolkit for scaling law research ⚖☆55Updated last year
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆63Updated 4 months ago
- Sparse and discrete interpretability tool for neural networks☆64Updated last year
- Supporting code for the blog post on modular manifolds.☆115Updated 4 months ago
- ☆56Updated last year
- ☆59Updated 2 months ago
- Code for the paper "Function-Space Learning Rates"☆25Updated 8 months ago
- ☆109Updated 6 months ago
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- ☆82Updated last year
- Experiments for efforts to train a new and improved t5☆76Updated last year