NVIDIA / NeMo-Skills
A project to improve skills of large language models
β255Updated this week
Alternatives and similar repositories for NeMo-Skills:
Users that are interested in NeMo-Skills are comparing it to the libraries listed below
- πΎ OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.β216Updated this week
- Implementation of paper Data Engineering for Scaling Language Models to 128K Contextβ453Updated 11 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"β162Updated last week
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"β298Updated last year
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"β392Updated 4 months ago
- β142Updated 2 months ago
- Reproducible, flexible LLM evaluationsβ172Updated 3 months ago
- Codes for the paper "βBench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718β312Updated 5 months ago
- β261Updated 7 months ago
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).β207Updated 3 weeks ago
- Scalable toolkit for efficient model alignmentβ740Updated this week
- Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paperβ127Updated 7 months ago
- RewardBench: the first evaluation tool for reward models.β521Updated 2 weeks ago
- Multipack distributed sampler for fast padding-free training of LLMsβ186Updated 7 months ago
- [ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuningβ348Updated 6 months ago
- "Improving Mathematical Reasoning with Process Supervision" by OPENAIβ107Updated last week
- β326Updated last month
- β253Updated last year
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β227Updated last week
- The HELMET Benchmarkβ120Updated last week
- The official evaluation suite and dynamic data release for MixEval.β231Updated 4 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)β204Updated 9 months ago
- Benchmarking LLMs with Challenging Tasks from Real Usersβ218Updated 4 months ago
- Official repository for ORPOβ443Updated 9 months ago
- LOFT: A 1 Million+ Token Long-Context Benchmarkβ176Updated last week
- [NeurIPS'24 Spotlight] Observational Scaling Lawsβ53Updated 5 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024β277Updated 2 weeks ago
- Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.β405Updated 10 months ago