huangyungaodq
Follow
Stars
RWKV v5, v6 infctx LoRA trainer with 4bit quantization,Cuda and Rocm supported, for training arbitary context sizes, to 10k and beyond!
RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!
This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the idea of SLAM_ASR and used the RWKV language model as the LLM…
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
RWKV (Receptance Weighted Key Value) is a RNN with Transformer-level performance
An open source implementation of the paper: "AN EVOLVED UNIVERSAL TRANSFORMER MEMORY"
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
📊 A minimalist, self-hosted WakaTime-compatible backend for coding statistics
High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
C++ implementation of BoT-SORT MOT algorithm with Re-ID and Camera Motion Compensation
MOT using deepsort and yolov3 with pytorch
Simple, online, and realtime tracking of multiple objects in a video sequence.
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
An open-source implementaion for fine-tuning Qwen2-VL series by Alibaba Cloud.
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
MagicPIG: LSH Sampling for Efficient LLM Generation
Support mixed-precsion inference with vllm