PotatoSpudowski / fastLLaMaLinks
fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backend.
☆409Updated 2 years ago
Alternatives and similar repositories for fastLLaMa
Users that are interested in fastLLaMa are comparing it to the libraries listed below
Sorting:
- SoTA Transformers with C-backend for fast inference on your CPU.☆309Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated 2 years ago
- Python bindings for llama.cpp☆197Updated 2 years ago
- ☆535Updated last year
- C++ implementation for BLOOM☆810Updated 2 years ago
- Tune any FALCON in 4-bit☆467Updated last year
- ☆415Updated last year
- ☆276Updated 2 years ago
- ☆458Updated last year
- Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes…☆147Updated last year
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…☆312Updated last year
- An Autonomous LLM Agent that runs on Wizcoder-15B☆335Updated 8 months ago
- Extend the original llama.cpp repo to support redpajama model.☆117Updated 9 months ago
- Harnessing the Memory Power of the Camelids☆146Updated last year
- Falcon LLM ggml framework with CPU and GPU support☆246Updated last year
- ☆406Updated 2 years ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆423Updated last year
- ggml implementation of BERT☆493Updated last year
- A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI…☆598Updated 2 years ago
- LLaMa retrieval plugin script using OpenAI's retrieval plugin☆324Updated 2 years ago
- Customizable implementation of the self-instruct paper.☆1,044Updated last year
- C++ implementation for 💫StarCoder☆453Updated last year
- Framework agnostic python runtime for RWKV models☆146Updated 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 …☆412Updated last year
- Official supported Python bindings for llama.cpp + gpt4all☆1,019Updated 2 years ago
- This repository contains code for extending the Stanford Alpaca synthetic instruction tuning to existing instruction-tuned models such as…☆352Updated last year
- A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer☆1,635Updated last year
- ☆543Updated 6 months ago
- Uses Auto-GPT with Llama.cpp☆386Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆585Updated 11 months ago