formll / resolving-scaling-law-discrepanciesLinks
☆20Updated last year
Alternatives and similar repositories for resolving-scaling-law-discrepancies
Users that are interested in resolving-scaling-law-discrepancies are comparing it to the libraries listed below
Sorting:
- Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)☆29Updated last week
- Efficient Scaling laws and collaborative pretraining.☆18Updated 2 weeks ago
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆31Updated 8 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated 5 months ago
- ☆33Updated 8 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- The repository contains code for Adaptive Data Optimization☆25Updated 9 months ago
- Exploration of automated dataset selection approaches at large scales.☆47Updated 7 months ago
- ☆17Updated last year
- Self-Supervised Alignment with Mutual Information☆21Updated last year
- ☆13Updated 3 months ago
- ☆19Updated 6 months ago
- ☆50Updated last year
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆14Updated 6 months ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆18Updated 10 months ago
- Codebase for Instruction Following without Instruction Tuning☆35Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆15Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆34Updated last month
- ☆15Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated 10 months ago
- ☆28Updated last year
- ☆21Updated last month
- ☆13Updated last month
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- ☆101Updated last year
- ☆27Updated 2 years ago
- ACL24☆10Updated last year
- Codebase for Context-aware Meta-learned Loss Scaling (CaMeLS). https://arxiv.org/abs/2305.15076.☆25Updated last year