The simplest, fastest repository for training/finetuning small-sized VLMs.
☆5,049Oct 27, 2025Updated 11 months ago
Alternatives and similar repositories for nanoVLM
Users that are interested in nanoVLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,322Aug 26, 2025Updated last year
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,907Apr 18, 2025Updated last year
- Nano vLLM☆15,832Apr 26, 2026Updated 5 months ago
- Everything about the SmolLM and SmolVLM family of models☆3,923Oct 6, 2026Updated last week
- Minimalistic large language model 3D-parallelism training☆2,841Oct 8, 2026Updated last week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- NanoGPT (124M) in 90 seconds☆5,944Sep 28, 2026Updated 2 weeks ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,872Updated this week
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆362Nov 2, 2025Updated 11 months ago
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆20,073Jan 30, 2026Updated 8 months ago
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,382Apr 13, 2026Updated 6 months ago
- A PyTorch native platform for training generative AI models☆5,802Updated this week
- Fully open reproduction of DeepSeek-R1☆26,481Oct 2, 2026Updated last week
- Minimal reproduction of DeepSeek R1-Zero☆13,252Feb 27, 2026Updated 7 months ago
- Our library for RL environments + evals☆4,704Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025☆7,423Sep 11, 2026Updated last month
- The best ChatGPT that $100 can buy.☆58,604Sep 7, 2026Updated last month
- 👀 Train a 65M-parameter VLM from scratch in just 2h!☆8,747Sep 22, 2026Updated 3 weeks ago
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.☆77,995Updated this week
- Train transformer language models with reinforcement learning.☆19,508Updated this week
- Efficient Triton Kernels for LLM Training☆6,659Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆93,782Updated this week
- Simple MPI implementation for prototyping or learning☆332Aug 6, 2025Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆63,776Nov 12, 2025Updated 11 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- SGLang is a high-performance serving framework for large language models and multimodal models.☆37,132Updated this week
- Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks☆4,439Updated this week
- slime is an LLM post-training framework for RL Scaling.☆8,661Updated this week
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆75,448Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,087Oct 5, 2026Updated last week
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,601Jan 12, 2025Updated last year
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆25,066Aug 12, 2024Updated 2 years ago
- Reference PyTorch implementation and models for DINOv3☆11,543Jul 15, 2026Updated 3 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,190Sep 19, 2026Updated 3 weeks ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conv…☆692Mar 10, 2025Updated last year
- Fast and memory-efficient exact attention☆25,134Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,769Jul 18, 2025Updated last year
- 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning☆28,139Updated this week
- Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜☆1,999Aug 12, 2026Updated 2 months ago
- 🤗 smolagents: a barebones library for agents that think in code.☆29,818Oct 6, 2026Updated last week
- PyTorch native post-training library☆5,815Sep 9, 2026Updated last month