Stars
Bench360 is a modular benchmarking suite for local LLM deployments. It offers a full-stack, extensible pipeline to evaluate the latency, throughput, quality, and cost of LLM inference on consumer a…
MediaWiki scraper: all your wiki articles in one highly compressed ZIM file
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
Python API to access and manipulate ELOG.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A curated list for Efficient Large Language Models
Enhancing Medical Question-Answering System through Advanced Information Retrieval Strategies and Integration of GPT-3.5
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Comparison of Language Model Inference Engines
Evaluating the Effectiveness of Transformer Layers in Wav2Vec 2.0, XLS-R, and Whisper for Speaker Identification Tasks
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
Janus-Series: Unified Multimodal Understanding and Generation Models
Code for MedCPT, a model for zero-shot biomedical information retrieval.
[ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links
A full spaCy pipeline and models for scientific/biomedical documents.
Official repository of the MIRAGE benchmark
Meditron is a suite of open-source medical Large Language Models (LLMs).
Official Implementation of NeurIPS 2024 paper "G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering""