Lists (1)
Stars
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Convert PDF to markdown quickly with high accuracy
Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
OCR, layout analysis, reading order, table recognition in 90+ languages
A framework for few-shot evaluation of language models.
Model interpretability and understanding for PyTorch
Tools for merging pretrained large language models.
Robust recipes to align language models with human and AI preferences
General technology for enabling AI capabilities w/ LLMs and MLLMs
PyTorch code and models for V-JEPA self-supervised learning from video.
Meditron is a suite of open-source medical Large Language Models (LLMs).
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Accelerating the development of large multimodal models (LMMs) with lmms-eval
The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
Reaching LLaMA2 Performance with 0.1M Dollars
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
[ACL 2024] Progressive LLaMA with Block Expansion.
An open science effort to benchmark legal reasoning in foundation models
A framework for merging models solving different tasks with different initializations into one multi-task model without any additional training
This is the official repository of our paper "MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine“
Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind
Multilingual Medicine: Model, Dataset, Benchmark, Code
Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answer based on user queries.