nisten / grokadamw
new optimizer
☆16Updated last month
Related projects: ⓘ
- ☆109Updated last month
- Fast approximate inference on a single GPU with sparsity aware offloading☆39Updated 8 months ago
- ☆48Updated 6 months ago
- A pipeline for LLM knowledge distillation☆68Updated last month
- an implementation of Self-Extend, to expand the context window via grouped attention☆117Updated 8 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated last year
- Latent Large Language Models☆16Updated 3 weeks ago
- ☆48Updated 11 months ago
- Experiments for efforts to train a new and improved t5☆76Updated 5 months ago
- ☆75Updated 3 weeks ago
- Testing LLM reasoning abilities with family relationship quizzes.☆40Updated 3 weeks ago
- Data preparation code for CrystalCoder 7B LLM☆42Updated 4 months ago
- ☆36Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆73Updated last month
- ☆29Updated 3 weeks ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆22Updated 6 months ago
- Full finetuning of large language models without large memory requirements☆94Updated 8 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated 3 months ago
- ☆21Updated 3 months ago
- Evaluating LLMs with CommonGen-Lite☆83Updated 6 months ago
- Collection of autoregressive model implementation☆62Updated 2 weeks ago
- Using open source LLMs to build synthetic datasets for direct preference optimization☆33Updated 6 months ago
- Small and Efficient Mathematical Reasoning LLMs☆69Updated 7 months ago
- Set of scripts to finetune LLMs☆36Updated 5 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated 5 months ago
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆28Updated 4 months ago
- Just a bunch of benchmark logs for different LLMs☆112Updated last month
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆67Updated last year
- Small, simple agent task environments for training and evaluation☆13Updated last week