TopOpenSourceAI
zh
← Back to scenarios

Foundation Models

Open-weight LLMs, fine-tuning stacks, and tooling around foundation models.

113 projects

See methodology for ranking rules; order uses public GitHub metrics within this scenario.

41–60 of 113

Rank Project Stars Forks
41 Graphormer

Graphormer is a general-purpose deep learning backbone for molecular modeling.

2.5K 376
42 Index-1.9B

A lightweight multilingual LLM

1.0K 51
43 TimeCraft

Official code for TimeCraft: A Time Series Generation Framework for Real-World Applications

1.1K 65
44 Ovis

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

1.5K 89
45 GLM-4.5

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

4.4K 473
46 StableLM

StableLM: Stability AI Language Models

15.7K 1.0K
47 ultravox

A fast multimodal LLM for real-time voice

4.6K 387
48 perception_models

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

2.4K 160
49 Chinese-LLaMA-Alpaca-3

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

2.0K 170
50 Chinese-XLNet

Pre-Trained Chinese XLNet（中文XLNet预训练模型）

1.6K 278
51 Chinese-ELECTRA

Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）

1.4K 165
52 lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

6.1K 517
53 ModernBERT

Bringing BERT into modernity via both architecture changes and scaling

1.7K 144
54 matmulfreellm

Implementation for MatMul-free LM.

3.1K 201
55 Show-o

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

2.0K 94
56 MiniMax-M2

MiniMax-M2, a model built for Max coding & agentic workflows.

2.6K 215
57 ChatLaw

ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

7.6K 618
58 cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

2.0K 140
59 Yi

A series of large language models trained from scratch by developers @01-ai

7.8K 498
60 Qwen2.5-Omni

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

4.1K 327
< Previous
/ 6
Next >