Davidqian123
Follow
Stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Fully open reproduction of DeepSeek-R1
Universal LLM Deployment Engine with ML Compilation
The official repo of Qwen (通义���问) chat & pretrained large language model proposed by Alibaba Cloud.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Unified framework for building enterprise RAG pipelines with small, specialized models
A framework for few-shot evaluation of language models.
On-device AI across mobile, embedded and edge for PyTorch
An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organiz…
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
AI for all: Build the large graph of the language models
No-code CLI designed for accelerating ONNX workflows
Build dynamic, secure APIs with FastAPI: Features DB integration, real-time WebSocket, streaming, and efficient request handling with middleware, powered by Starlette and Pydantic.
An interactive AI character with voice input, voice output, and profile image generation—all running locally with Nexa SDK and powered by Llama3 Uncensored Model. Enjoy a private and immersive expe…
Python Concurrency Web Crawler, and Redis
Nexa AI PDF Chatbot using Nexa SDK
🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.