austinsilveria / tricksyLinks
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
Sorting:
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- Simple GRPO scripts and configurations.☆59Updated 6 months ago
- Scripts to create your own moe models using mlx☆90Updated last year
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 8 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- ☆53Updated 8 months ago
- ☆87Updated last year
- Let's create synthetic textbooks together :)☆75Updated last year
- QLoRA with Enhanced Multi GPU Support☆37Updated last year
- Collection of autoregressive model implementation☆86Updated 3 months ago
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated last year
- ☆15Updated last year
- GPT-4 Level Conversational QA Trained In a Few Hours☆63Updated 11 months ago
- Data preparation code for CrystalCoder 7B LLM☆45Updated last year
- ☆66Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated last year
- Cerule - A Tiny Mighty Vision Model☆66Updated 10 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- GPT-2 small trained on phi-like data☆67Updated last year
- Finetune any model on HF in less than 30 seconds☆57Updated 2 weeks ago
- ☆58Updated 3 weeks ago
- ☆115Updated 7 months ago
- ☆51Updated last year
- ☆26Updated last year
- ☆74Updated last year
- Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first app…☆168Updated last year
- ☆134Updated 11 months ago
- ☆37Updated last year