The simplest, fastest repository for training/finetuning small-sized VLMs.
☆4,892Oct 27, 2025Updated 7 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☆2,216Aug 26, 2025Updated 9 months ago
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,860Apr 18, 2025Updated last year
- Everything about the SmolLM and SmolVLM family of models☆3,805May 26, 2026Updated 2 weeks ago
- A PyTorch native platform for training generative AI models☆5,435Updated this week
- Fully open reproduction of DeepSeek-R1☆26,295Apr 2, 2026Updated 2 months ago
- 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.
- NanoGPT (124M) in 90 seconds☆5,385Updated this week
- Minimal reproduction of DeepSeek R1-Zero☆13,160Feb 27, 2026Updated 3 months ago
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,299Apr 13, 2026Updated 2 months ago
- Minimalistic large language model 3D-parallelism training☆2,715May 26, 2026Updated 2 weeks ago
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,577Jan 12, 2025Updated last year
- Train transformer language models with reinforcement learning.☆18,613Updated this week
- This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025☆7,366May 5, 2025Updated last year
- Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.☆66,153Updated this week
- Efficient Triton Kernels for LLM Training☆6,430Updated this 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.
- Nano vLLM☆13,925Apr 26, 2026Updated last month
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,763Jul 18, 2025Updated 10 months ago
- Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜☆1,940May 26, 2026Updated 2 weeks ago
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆19,353Jan 30, 2026Updated 4 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆82,482Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,850Updated this week
- A course on aligning smol models.☆6,657May 26, 2026Updated 2 weeks ago
- PyTorch native post-training library☆5,768Updated this week
- 🤗 smolagents: a barebones library for agents that think in code.☆27,815Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆59,420Nov 12, 2025Updated 7 months ago
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆24,864Aug 12, 2024Updated last year
- Fast and memory-efficient exact attention☆24,111Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,219Aug 22, 2025Updated 9 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆28,886Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆13,414Updated this week
- LLM training in simple, raw C/CUDA☆30,150Jun 26, 2025Updated 11 months ago
- Witness the aha moment of VLM with less than $3.☆4,060May 19, 2025Updated last year
- VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…☆3,817Mar 12, 2026Updated 3 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,549Jul 1, 2024Updated last year
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.☆3,464May 19, 2025Updated last year
- LLM101n: Let's build a Storyteller☆37,259Aug 1, 2024Updated last year
- 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning☆24,867Updated this week
- Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving stat…☆1,580Jun 14, 2025Updated 11 months ago
- PyTorch native quantization and sparsity for training and inference☆2,847Jun 5, 2026Updated last week
- Our library for RL environments + evals☆4,187Updated this week