-
AntGroup
- Shanghai & Suzhou
-
21:02
(UTC +08:00)
Stars
DLRover: An Automatic Distributed Deep Learning System
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
[ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"
Retrieval and Retrieval-augmented LLMs
Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
🚌 The IK Analysis plugin integrates Lucene IK analyzer into Elasticsearch and OpenSearch, support customized dictionary.
[ACL'24 Outstanding] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark
YaRN: Efficient Context Window Extension of Large Language Models
DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
中文Mixtral-8x7B(Chinese-Mixtral-8x7B)
Official inference library for Mistral models
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
LlamaIndex is a data framework for your LLM applications
利用HuggingFace的官方下载工具从镜像网站进行高速下载。
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
A tool for extracting plain text from Wikipedia dumps
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
library supporting NLP and CV research on scientific papers
State-of-the-art 2D and 3D Face Analysis Project