LLMs
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
This is the official repository for M2UGen
Seamlessly integrate LLMs into scikit-learn.
QLoRA: Efficient Finetuning of Quantized LLMs
Collection of leaked system prompts
[NeurlPS D&B 2024] Generative AI for Math: MathPile
A high-throughput and memory-efficient inference and serving engine for LLMs
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
CLI platform to experiment with codegen. Precursor to: htt 8000 ps://lovable.dev
Rapid prototyping of web apps using plain english 👶🤖
LLaVA-JP is a Japanese VLM trained by LLaVA method
OpenChat: Advancing Open-source Language Models with Imperfect Data
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
Build and iterate on your UI 10x faster with AI - right from your own IDE ☕️
BLOOM+1: Adapting BLOOM model to support a new unseen language
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
🤖✨🗺 charites-ai - AI that can generate json files according to Mapbox style specification based on natural language instructions
Distribute and run LLMs with a single file.
The production toolkit for LLMs. Observability, prompt management and evaluations.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Inference Llama 2 in one file of pure JavaScript(HTML)
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
A curated list of resources for graph prompting methods