SkunkworksAI / hydra-moeLinks
☆415Updated last year
Alternatives and similar repositories for hydra-moe
Users that are interested in hydra-moe are comparing it to the libraries listed below
Sorting:
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆423Updated last year
- Generate textbook-quality synthetic LLM pretraining data☆500Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100s☆714Updated last year
- A bagel, with everything.☆321Updated last year
- batched loras☆343Updated last year
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆222Updated last year
- Inference code for Persimmon-8B☆415Updated last year
- Inference code for Mistral and Mixtral hacked up into original Llama implementation☆371Updated last year
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆698Updated last year
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆197Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆692Updated 10 months ago
- Fast & more realistic evaluation of chat language models. Includes leaderboard.☆187Updated last year
- ☆95Updated last year
- Customizable implementation of the self-instruct paper.☆1,044Updated last year
- ☆541Updated 9 months ago
- Merge Transformers language models by use of gradient parameters.☆206Updated 10 months ago
- Multipack distributed sampler for fast padding-free training of LLMs☆191Updated 10 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆239Updated last year
- ☆199Updated last year
- ☆92Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆585Updated 11 months ago
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆724Updated last year
- Code for fine-tuning Platypus fam LLMs using LoRA☆628Updated last year
- The repository for the code of the UltraFastBERT paper☆516Updated last year
- Tune any FALCON in 4-bit☆467Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 10 months ago
- This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and bench…☆588Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated 2 years ago