pratyushasharma / laserView external linksLinks
The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
☆390Jul 9, 2024Updated last year
Alternatives and similar repositories for laser
Users that are interested in laser are comparing it to the libraries listed below
Sorting:
- This is our own implementation of 'Layer Selective Rank Reduction'☆240May 26, 2024Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆180May 2, 2024Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆640Mar 4, 2024Updated last year
- Tools for merging pretrained large language models.☆6,783Jan 26, 2026Updated 2 weeks ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,705Jun 25, 2024Updated last year
- ☆129Jan 22, 2024Updated 2 years ago
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,672Oct 28, 2024Updated last year
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆116Dec 30, 2023Updated 2 years ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Jan 7, 2024Updated 2 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,316Mar 6, 2025Updated 11 months ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆279Nov 3, 2023Updated 2 years ago
- Codebase for Merging Language Models (ICML 2024)☆864May 5, 2024Updated last year
- The repository for the code of the UltraFastBERT paper☆518Mar 24, 2024Updated last year
- Fast approximate inference on a single GPU with sparsity aware offloading☆39Jan 4, 2024Updated 2 years ago
- ☆577Oct 29, 2024Updated last year
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,407Apr 11, 2024Updated last year
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…☆1,105Oct 7, 2024Updated last year
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,234May 8, 2024Updated last year
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆866Aug 20, 2024Updated last year
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆667Jun 1, 2024Updated last year
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆887Nov 26, 2025Updated 2 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,011Sep 4, 2024Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆396Feb 24, 2024Updated last year
- Robust recipes to align language models with human and AI preferences☆5,495Sep 8, 2025Updated 5 months ago
- Code for paper titled "Towards the Law of Capacity Gap in Distilling Language Models"☆102Jul 9, 2024Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,180Jan 27, 2026Updated 2 weeks ago
- ☆203Dec 5, 2024Updated last year
- For releasing code related to compression methods for transformers, accompanying our publications☆455Jan 16, 2025Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆191Apr 17, 2025Updated 9 months ago
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆202Jun 22, 2023Updated 2 years ago
- ☆415Nov 2, 2023Updated 2 years ago
- Full finetuning of large language models without large memory requirements☆94Sep 22, 2025Updated 4 months ago
- Simple Model Similarities Analysis☆21Feb 3, 2024Updated 2 years ago
- ☆91Aug 18, 2024Updated last year
- ☆166Aug 8, 2025Updated 6 months ago
- GPT-2 small trained on phi-like data☆68Feb 18, 2024Updated last year
- MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning☆362Aug 7, 2024Updated last year
- ☆68Aug 16, 2024Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Jul 28, 2024Updated last year