shawwn / website
The code that runs my blog: https://blog.gpt4.org/
☆10Updated 3 years ago
Related projects: ⓘ
- A library for incremental loading of large PyTorch checkpoints☆56Updated last year
- Unleash the full potential of exascale LLMs on consumer-class GPUs, proven by extensive benchmarks, with no long-term adjustments and min…☆23Updated last week
- Efficiently computing & storing token n-grams from large corpora☆15Updated 2 weeks ago
- A client library for LAION's effort to filter CommonCrawl with CLIP, building a large scale image-text dataset.☆31Updated last year
- 33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU☆11Updated 4 months ago
- Tools for encoding Magic: The Gathering cards into a form suitable for AI text generation☆17Updated 3 years ago
- Web page with political compass quiz results for open LLMs☆37Updated 7 months ago
- implementation of https://arxiv.org/pdf/2312.09299☆19Updated 2 months ago
- Trying to deconstruct RWKV in understandable terms☆14Updated last year
- Simple, Fast, Parallel Huggingface GGML model downloader written in python☆24Updated last year
- Evolutionary Search for expert-level performance on any task with environmental feedback☆14Updated 7 months ago
- Experimental sampler to make LLMs more creative☆29Updated last year
- Python wrapper for Ferret☆42Updated 2 years ago
- Low-Rank Adaptation of Large Language Models clean implementation☆9Updated last year
- AI cover model for your own voice.☆35Updated last month
- Python script to quickly generate a Font Awesome icon imposed on a background for steering AI image generation.☆53Updated 2 years ago
- Testing KAN-based text generation GPT models☆14Updated 4 months ago
- Run Vision LLMs, TTS and STT APIs. Website and API for https://text-generator.io☆25Updated last month
- iterate quickly with llama.cpp hot reloading. use the llama.cpp bindings with bun.sh☆45Updated 10 months ago
- General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). …☆35Updated last week
- Senna is an advanced AI-powered search engine designed to provide users with immediate answers to their queries by leveraging natural lan…☆19Updated 2 weeks ago
- URL downloader supporting checkpointing and continuous checksumming.☆19Updated 9 months ago
- ☆40Updated last year
- LLama implementations benchmarking framework☆10Updated 10 months ago
- Mistral-7B finetuned for function calling☆14Updated 7 months ago
- ☆17Updated 7 months ago
- Simple implementation of a GPT (training and inference) in PyTorch.☆9Updated 9 months ago
- Fast inference of Instruct tuned LLaMa on your personal devices.☆22Updated last year
- Simple script to quiz LLMs☆24Updated 7 months ago
- A QT GUI for large language models☆23Updated 8 months ago