47,133 repositories indexed
25–48 of 59 · Most stars
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
A framework for few-shot evaluation of language models.
An open source implementation of CLIP.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Pocket Flow: Codebase to Tutorial
Hierarchical Reasoning Model Official Release
An open-source, tool-augmented conversational language model from Fudan University
The official GitHub page for the survey paper "A Survey of Large Language Models".
A PyTorch-based Speech Toolkit
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models
A collection of libraries to optimise AI model performances
Open-source offline translation library written in Python
[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
Official release of the ProGen models
BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).