Trending Transformer Models
Models with the biggest quality score improvements over the last 6 days.
| # | Model | Change | Score | Tier |
|---|---|---|---|---|
| 1 |
kha-white/manga-ocr
Optical character recognition for Japanese text, with the main focus being... |
+17 | 64 | Established |
| 2 |
SwanHubX/SwanLab
⚡️SwanLab - an open-source, modern-design AI training tracking and... |
+17 | 89 | Verified |
| 3 |
OpenVoiceOS/ovos-audio-transformer-plugin-ggwave
data over sound plugin |
+17 | 52 | Established |
| 4 |
Riko0/messenger_logger_callback
messenger-logger-callback — Send ML training logs to Telegram. Standalone... |
+15 | 31 | Emerging |
| 5 |
rxn4chemistry/rxn-onmt-models
Training of OpenNMT-based RXN models |
+14 | 45 | Emerging |
| 6 |
lpalbou/model-quantizer
Effortlessly quantize, benchmark, and publish Hugging Face models with... |
+14 | 25 | Experimental |
| 7 |
ndoll1998/active-transformers
Active Learning for Transformer with focus on Sequence Tagging tasks |
+13 | 24 | Experimental |
| 8 |
kmaurinjones/AllMeans
Automatic topic modelling using minimal external input and computational resources |
+13 | 30 | Emerging |
| 9 |
yingding/applyllm
A python package for applying LLM with LangChain and Hugging Face on local... |
+13 | 30 | Emerging |
| 10 |
Blaizzy/mlx-vlm
MLX-VLM is a package for inference and fine-tuning of Vision Language Models... |
+12 | 89 | Verified |
| 11 |
touhi99/askagent
Simple mac/unix terminal assistant with LLM agents capable of various tasks |
+12 | 35 | Emerging |
| 12 |
mim-solutions/mim_nlp
A Python package with ready-to-use models for various NLP tasks and text... |
+12 | 23 | Experimental |
| 13 |
sagorbrur/fillblank
Fill The Blank |
+12 | 23 | Experimental |
| 14 |
duck4i/retro-ui
Retro Llama |
+11 | 14 | Experimental |
| 15 |
BradyFU/Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models |
+11 | 56 | Established |
| 16 |
argosopentech/argos-translate
Open-source offline translation library written in Python |
+10 | 58 | Established |
| 17 |
cui-shaobo/causal-strength
evaluating the causal strength between cause and effect |
+9 | 20 | Experimental |
| 18 |
earthai-tech/fusionlab-learn
fusionlab-learn: Igniting Next-Gen Temporal Fusion Architectures |
+9 | 33 | Emerging |
| 19 |
ash-01xor/Imgcap
A CLI to generate captions for images |
+9 | 12 | Experimental |
| 20 |
changyeyu/LLM-RL-Visualized
🌟100+ 原创 LLM / RL 原理图📚,《大模型算法》作者巨献!💥(100+ LLM/RL Algorithm Maps ) |
+9 | 58 | Established |
| 21 |
levashi/reprobe
Phase-aware LLM activation steering and linear probing. A memory-efficient,... |
+9 | 33 | Emerging |
| 22 |
ThilinaRajapakse/simpletransformers
Transformers for Information Retrieval, Text Classification, NER, QA,... |
+8 | 75 | Verified |
| 23 |
AutoGPTQ/AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on... |
+7 | 46 | Emerging |
| 24 |
labmlai/annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side... |
+7 | 56 | Established |
| 25 |
stas00/ml-engineering
Machine Learning Engineering Open Book |
+7 | 60 | Established |
| 26 |
xorbitsai/inference
Swap GPT for any LLM by changing a single line of code. Xinference lets you... |
+7 | 89 | Verified |
| 27 |
hiyouga/LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) |
+7 | 70 | Verified |
| 28 |
LLMBook-zh/LLMBook-zh.github.io
《大语言模型》作者:赵鑫,李军毅,周昆,唐天一,文继荣 |
+7 | 39 | Emerging |
| 29 |
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss,... |
+7 | 94 | Verified |
| 30 |
AI-Hypercomputer/maxtext
A simple, performant and scalable Jax LLM! |
+7 | 92 | Verified |
| 31 |
mosaicml/llm-foundry
LLM training code for Databricks foundation models |
+7 | 71 | Verified |
| 32 |
h2oai/h2o-llmstudio
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs.... |
+7 | 66 | Established |
| 33 |
IDEA-CCNL/Fengshenbang-LM
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系,成为中文AIGC和认知智能的基础设施。 |
+7 | 46 | Emerging |
| 34 |
MiniMax-AI/MiniMax-01
The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model... |
+7 | 48 | Emerging |
| 35 |
deepseek-ai/Janus
Janus-Series: Unified Multimodal Understanding and Generation Models |
+7 | 47 | Emerging |
| 36 |
fixie-ai/ultravox
A fast multimodal LLM for real-time voice |
+7 | 51 | Established |
| 37 |
datawhalechina/llm-cookbook
面向开发者的 LLM 入门教程,吴恩达大模型系列课程中文版 |
+7 | 41 | Emerging |
| 38 |
multimodal-art-projection/YuE
YuE: Open Full-song Music Generation Foundation Model, something similar to... |
+7 | 49 | Emerging |
| 39 |
b4rtaz/distributed-llama
Distributed LLM inference. Connect home devices into a powerful cluster to... |
+7 | 55 | Established |
| 40 |
qingsongedu/time-series-transformers-review
A professionally curated list of awesome resources (paper, code, data, etc.)... |
+7 | 46 | Emerging |
| 41 |
EleutherAI/gpt-neo
An implementation of model parallel GPT-2 and GPT-3-style models using the... |
+7 | 47 | Emerging |
| 42 |
EleutherAI/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs,... |
+7 | 58 | Established |
| 43 |
0hq/WebGPT
Run GPT model on the browser with WebGPU. An implementation of GPT inference... |
+7 | 44 | Emerging |
| 44 |
jingyaogong/minimind
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h! |
+7 | 64 | Established |
| 45 |
VainF/Torch-Pruning
[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision... |
+7 | 69 | Established |
| 46 |
OFA-Sys/Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and... |
+7 | 48 | Emerging |
| 47 |
cmhungsteve/Awesome-Transformer-Attention
An ultimately comprehensive paper list of Vision Transformer/Attention,... |
+7 | 38 | Emerging |
| 48 |
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step |
+7 | 69 | Established |
| 49 |
huggingface/transformers.js
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly... |
+7 | 68 | Established |
| 50 |
tensorzero/tensorzero
TensorZero is an open-source stack for industrial-grade LLM applications. It... |
+7 | 89 | Verified |
| 51 |
mistralai/mistral-inference
Official inference library for Mistral models |
+7 | 56 | Established |
| 52 |
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on... |
+7 | 69 | Established |
| 53 |
bitsandbytes-foundation/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch. |
+7 | 90 | Verified |
| 54 |
NexaAI/nexa-sdk
Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and... |
+7 | 57 | Established |
| 55 |
transformerlab/transformerlab-app
The open source research environment for AI researchers to seamlessly train,... |
+7 | 71 | Verified |
| 56 |
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models |
+7 | 54 | Established |
| 57 |
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5,... |
+7 | 91 | Verified |
| 58 |
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs |
+7 | 100 | Verified |
| 59 |
mudler/LocalAI
:robot: The free, Open Source alternative to OpenAI, Claude and others.... |
+7 | 70 | Verified |
| 60 |
gpustack/gpustack
Performance-optimized AI inference on your GPUs. Unlock superior throughput... |
+7 | 71 | Verified |
| 61 |
mlabonne/llm-datasets
Curated list of datasets and tools for post-training. |
+7 | 53 | Established |
| 62 |
rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step |
+7 | 71 | Verified |
| 63 |
huggingface/optimum
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and... |
+7 | 90 | Verified |
| 64 |
pytorch/ao
PyTorch native quantization and sparsity for training and inference |
+7 | 74 | Verified |
| 65 |
AI4Finance-Foundation/FinGPT
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We... |
+7 | 82 | Verified |
| 66 |
huggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine... |
+7 | 100 | Verified |
| 67 |
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V... |
+7 | 47 | Emerging |
| 68 |
DAMO-NLP-SG/Video-LLaMA
[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language... |
+7 | 46 | Emerging |
| 69 |
Instruction-Tuning-with-GPT-4/GPT-4-LLM
Instruction Tuning with GPT-4 |
+7 | 45 | Emerging |
| 70 |
CLUEbenchmark/CLUE
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets,... |
+7 | 49 | Emerging |
| 71 |
PhoebusSi/Alpaca-CoT
We unified the interfaces of instruction-tuning data (e.g., CoT data),... |
+7 | 45 | Emerging |
| 72 |
HqWu-HITCS/Awesome-Chinese-LLM
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。 |
+7 | 40 | Emerging |
| 73 |
LianjiaTech/BELLE
BELLE: Be Everyone's Large Language model Engine(开源中文对话大模型) |
+7 | 46 | Emerging |
| 74 |
Facico/Chinese-Vicuna
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model ——... |
+7 | 48 | Emerging |
| 75 |
datawhalechina/llms-from-scratch-cn
仅需Python基础,从0构建大语言模型;从0逐步构建GLM4\Llama3\RWKV6, 深入理解大模型原理 |
+7 | 48 | Emerging |
| 76 |
cocktailpeanut/dalai
The simplest way to run LLaMA on your local machine |
+7 | 38 | Emerging |
| 77 |
ashishpatel26/LLM-Finetuning
LLM Finetuning with peft |
+7 | 45 | Emerging |
| 78 |
alibaba/MNN
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba,... |
+7 | 93 | Verified |
| 79 |
higgsfield-ai/higgsfield
Fault-tolerant, highly scalable GPU orchestration, and a machine learning... |
+7 | 49 | Emerging |
| 80 |
Tiiny-AI/PowerInfer
High-speed Large Language Model Serving for Local Deployment |
+7 | 54 | Established |
| 81 |
run-llama/LlamaIndexTS
Data framework for your LLM applications. Focus on server side solution |
+7 | 65 | Established |
| 82 |
sgl-project/sglang
SGLang is a high-performance serving framework for large language models and... |
+7 | 100 | Verified |
| 83 |
HandsOnLLM/Hands-On-Large-Language-Models
Official code repo for the O'Reilly Book - "Hands-On Large Language Models" |
+7 | 57 | Established |
| 84 |
OptimalScale/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation... |
+7 | 59 | Established |
| 85 |
fla-org/flash-linear-attention
🚀 Efficient implementations of state-of-the-art linear attention models |
+7 | 89 | Verified |
| 86 |
intel/neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity;... |
+7 | 90 | Verified |
| 87 |
huggingface/text-generation-inference
Large Language Model Text Generation Inference |
+7 | 82 | Verified |
| 88 |
baichuan-inc/Baichuan-7B
A large-scale 7B pretraining language model developed by BaiChuan-Inc. |
+7 | 45 | Emerging |
| 89 |
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any... |
+7 | 88 | Verified |
| 90 |
EricLBuehler/mistral.rs
Fast, flexible LLM inference |
+7 | 62 | Established |
| 91 |
jadore801120/attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need". |
+7 | 51 | Established |
| 92 |
OpenNMT/OpenNMT-py
Open Source Neural Machine Translation and (Large) Language Models in PyTorch |
+7 | 76 | Verified |
| 93 |
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training |
+7 | 90 | Verified |
| 94 |
NielsRogge/Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace. |
+7 | 64 | Established |
| 95 |
zyds/transformers-code
手把手带你实战 Huggingface Transformers 课程视频同步更新在B站与YouTube |
+7 | 40 | Emerging |
| 96 |
huggingface/course
The Hugging Face course on Transformers |
+7 | 67 | Established |
| 97 |
ymcui/Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs) |
+7 | 48 | Emerging |
| 98 |
LlamaFamily/Llama-Chinese
Llama中文社区,实时汇总最新Llama学习资料,构建最好的中文Llama大模型开源生态,完全开源可商用 |
+7 | 39 | Emerging |
| 99 |
ymcui/Chinese-LLaMA-Alpaca-2
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs... |
+7 | 47 | Emerging |
| 100 |
yangjianxin1/Firefly
Firefly:... |
+7 | 37 | Emerging |