Mini_RWKV_V7_LM

Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

🚀🚀 「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!

🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone

AndroidStudio中文插件(官方修改版本）

Longformer: The Long-Document Transformer

A pytorch &keras implementation and demo of Fastformer.

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

Whisper-Flamingo [Interspeech 2024] and mWhisper-Flamingo [IEEE SPL 2025] for Audio-Visual Speech Recognition and Translation

GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Model compression for ONNX

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Fork of SageAttention for Windows wheels and easy installation

Light Image Video Generation Inference Framework

Official repository for LTX-Video

A high-throughput and memory-efficient inference and serving engine for LLMs (Windows build & kernels)

A unified inference and post-training framework for accelerated video generation.

8GB optimized WAN2.2 T2V/I2V-A14B, long video generation 30 sec+

Wan: Open and Advanced Large-Scale Video Generative Models