Aratako / Task-Vector-Merge-Optimzier
☆14Updated 10 months ago
Alternatives and similar repositories for Task-Vector-Merge-Optimzier:
Users that are interested in Task-Vector-Merge-Optimzier are comparing it to the libraries listed below
- A repository for research on medium sized language models.☆76Updated 8 months ago
- Unofficial Implementation of Evolutionary Model Merging☆33Updated 10 months ago
- entropix style sampling + GUI☆25Updated 3 months ago
- Plug in & Play Pytorch Implementation of the paper: "Evolutionary Optimization of Model Merging Recipes" by Sakana AI☆28Updated 3 months ago
- ☆48Updated 3 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆31Updated 6 months ago
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" given…☆14Updated last year
- ☆31Updated 7 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated 11 months ago
- Checkpointable dataset utilities for foundation model training☆32Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆54Updated 5 months ago
- ☆27Updated last year
- Modified Beam Search with periodical restart☆12Updated 5 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆36Updated last year
- Support Continual pre-training & Instruction Tuning forked from llama-recipes☆31Updated 11 months ago
- ☆24Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆24Updated 4 months ago
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆42Updated 6 months ago
- Implementation of "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆42Updated 3 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆42Updated last year
- Minimal implementation of the Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models paper (ArXiv 20232401.01335)☆29Updated 11 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 11 months ago
- Collection of autoregressive model implementation☆81Updated this week
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …☆10Updated last year