andersonbcdefg / dpo-lora
direct preference optimization with only 1 model copy :)
☆12Updated 11 months ago
Related projects: ⓘ
- ☆55Updated 9 months ago
- Simplex Random Feature attention, in PyTorch☆71Updated 11 months ago
- A repository of prompts and Python scripts for intelligent transformation of raw text into diverse formats.☆29Updated last year
- Public Inflection Benchmarks☆69Updated 6 months ago
- Sparse autoencoders for Contra text embedding models☆24Updated 4 months ago
- ☆48Updated 11 months ago
- ☆40Updated 4 months ago
- A repository of projects and datasets under active development by Alignment Lab AI☆23Updated 8 months ago
- KMD is a collection of conversational exchanges between patients and doctors on various medical topics. It aims to capture the intricaci…☆23Updated 10 months ago
- Experiments for efforts to train a new and improved t5☆76Updated 5 months ago
- ☆29Updated 2 weeks ago
- Latent Diffusion Language Models☆66Updated last year
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆60Updated 4 months ago
- ☆22Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs. Now, with kittens!☆45Updated last month
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆67Updated last year
- ☆43Updated this week
- Small, simple agent task environments for training and evaluation☆13Updated last week
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆42Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆18Updated 2 months ago
- Understanding how features learned by neural networks evolve throughout training☆30Updated this week
- ☆38Updated this week
- Grokking on modular arithmetic in less than 150 epochs in MLX☆10Updated 3 weeks ago
- ☆25Updated this week
- Cerule - A Tiny Mighty Vision Model☆67Updated 2 weeks ago
- Code repository for the c-BTM paper☆105Updated 11 months ago
- Data preparation code for CrystalCoder 7B LLM☆42Updated 4 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- A library for squeakily cleaning and filtering language datasets.☆45Updated last year
- alternative way to calculating self attention☆18Updated 3 months ago