johnsmith0031 / alpaca_lora_4bit
☆535Updated last year
Alternatives and similar repositories for alpaca_lora_4bit:
Users that are interested in alpaca_lora_4bit are comparing it to the libraries listed below
- ☆459Updated last year
- Tune any FALCON in 4-bit☆466Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆422Updated last year
- Quantized inference code for LLaMA models☆1,048Updated 2 years ago
- Customizable implementation of the self-instruct paper.☆1,043Updated last year
- Alpaca dataset from Stanford, cleaned and curated☆1,552Updated 2 years ago
- ☆405Updated 2 years ago
- This repository contains code for extending the Stanford Alpaca synthetic instruction tuning to existing instruction-tuned models such as…☆351Updated last year
- LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions☆821Updated last year
- C++ implementation for 💫StarCoder☆453Updated last year
- 4 bits quantization of LLaMA using GPTQ☆3,053Updated 9 months ago
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆720Updated 11 months ago
- fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backe…☆410Updated last year
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …☆414Updated last year
- batched loras☆341Updated last year
- A bagel, with everything.☆319Updated last year
- ☆543Updated 4 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated last year
- Simple, hackable and fast implementation for training/finetuning medium-sized LLaMA-based models☆162Updated last week
- Merge Transformers language models by use of gradient parameters.☆206Updated 8 months ago
- C++ implementation for BLOOM☆809Updated last year
- Repo for fine-tuning Casual LLMs☆454Updated last year
- SoTA Transformers with C-backend for fast inference on your CPU.☆311Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆686Updated 8 months ago
- Official repository for LongChat and LongEval☆519Updated 11 months ago
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…☆310Updated last year
- Fast Inference Solutions for BLOOM☆561Updated 6 months ago
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆452Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆576Updated 9 months ago
- A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer☆1,631Updated last year