Alignment-Lab-AI / Dataset-Conversion-Toolkit
a set of scripts to easily convert all training data from huggingface into alpaca instruct or sharegpt format, which should allow for ease of use with any trainer
☆12Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for Dataset-Conversion-Toolkit
- ☆18Updated 3 weeks ago
- ☆53Updated 5 months ago
- A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.☆53Updated this week
- entropix style sampling + GUI☆25Updated 2 weeks ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆20Updated 9 months ago
- A pipeline parallel training script for LLMs.☆83Updated this week
- Gradio based tool to run opensource LLM models directly from Huggingface☆87Updated 4 months ago
- All the world is a play, we are but actors in it.☆47Updated 4 months ago
- ☆27Updated last year
- A framework for evaluating function calls made by LLMs☆34Updated 3 months ago
- After my server ui improvements were successfully merged, consider this repo a playground for experimenting, tinkering and hacking around…☆56Updated 2 months ago
- GPT-4 Level Conversational QA Trained In a Few Hours☆54Updated 2 months ago
- A repository to store helpful information and emerging insights in regard to LLMs☆20Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 8 months ago
- ☆64Updated 5 months ago
- Automated testing and benchmarking for code generation agents.☆17Updated last year
- LLM reads a paper and produce a working prototype☆34Updated this week
- Fast approximate inference on a single GPU with sparsity aware offloading☆38Updated 10 months ago
- run ollama & gguf easily with a single command☆47Updated 5 months ago
- Official homepage for "Self-Harmonized Chain of Thought"☆83Updated last month
- Terminal Voice Assistant is a powerful and flexible tool designed to help users interact with their terminal using natural language comma…☆16Updated 5 months ago
- The hearth of The Pulsar App, fast, secure and shared inference with modern UI☆35Updated 2 weeks ago
- Scripts to create your own moe models using mlx☆86Updated 8 months ago
- Large Model Proxy is designed to make it easy to run multiple resource-heavy Large Models (LM) on the same machine with limited amount of…☆46Updated last month
- ASR + diarization model server with speculative decoding☆49Updated 5 months ago
- Let's create synthetic textbooks together :)☆70Updated 9 months ago
- ☆104Updated 7 months ago
- Easily view and modify JSON datasets for large language models☆62Updated last month
- Experimental sampler to make LLMs more creative☆30Updated last year