austinsilveria / tricksy
Fast approximate inference on a single GPU with sparsity aware offloading
☆38Updated last year
Alternatives and similar repositories for tricksy:
Users that are interested in tricksy are comparing it to the libraries listed below
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆21Updated 3 months ago
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- [WIP] Transformer to embed Danbooru labelsets☆13Updated 11 months ago
- ☆48Updated 4 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Data preparation code for CrystalCoder 7B LLM☆44Updated 10 months ago
- entropix style sampling + GUI☆25Updated 4 months ago
- ☆65Updated 9 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated last year
- tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.☆38Updated 6 months ago
- ☆15Updated last year
- Score LLM pretraining data with classifiers☆54Updated last year
- Scripts to create your own moe models using mlx☆89Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- ☆63Updated 5 months ago
- ☆49Updated last year
- Cerule - A Tiny Mighty Vision Model☆67Updated 6 months ago
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- RWKV-7: Surpassing GPT☆81Updated 4 months ago
- ☆73Updated last year
- ☆31Updated 9 months ago
- GPT-4 Level Conversational QA Trained In a Few Hours☆58Updated 6 months ago
- ☆20Updated last year
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 3 weeks ago
- QLoRA for Masked Language Modeling☆21Updated last year