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:
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated 2 years ago
- Scripts to create your own moe models using mlx☆90Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated last week
- ☆55Updated 11 months ago
- Simple GRPO scripts and configurations.☆59Updated 8 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- Data preparation code for CrystalCoder 7B LLM☆45Updated last year
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 11 months ago
- GPT-4 Level Conversational QA Trained In a Few Hours☆65Updated last year
- Let's create synthetic textbooks together :)☆75Updated last year
- ☆67Updated last year
- ☆88Updated last year
- QLoRA with Enhanced Multi GPU Support☆37Updated 2 years ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆35Updated last year
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- Library to facilitate pruning of LLMs based on context☆32Updated last year
- entropix style sampling + GUI☆27Updated 11 months ago
- Collection of autoregressive model implementation☆86Updated 6 months ago
- ☆51Updated last year
- Eh, simple and works.☆27Updated last year
- ☆62Updated 3 months ago
- ☆73Updated 2 years ago
- ☆20Updated last year
- ☆49Updated 8 months ago
- inference code for mixtral-8x7b-32kseqlen☆102Updated last year
- Score LLM pretraining data with classifiers☆54Updated last year
- GPT-2 small trained on phi-like data☆67Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated last year
- ☆136Updated last year