AI-Natural-Language-Processing-Lab's repositories
GlotLID-language-identification-model
Language Identification tool for more than 1600 languages (EMNLP 2023).
streaming-llm-Streaming-Language-Models-with-Attention-Sinks
Efficient Streaming Language Models with Attention Sinks
ToRA-LLM-Agents-designed-to-solve-challenging-mathematical-reasoning-problems
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools.
graphologue-Exploring-LLM-Responses-with-Interactive-Diagrams
Use GPT-4 to stream diagrams, instead of tokens, in real-time! (UIST 2023 Paper)
LLM-Agent-Paper-List
The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
agents-Framework-for-Autonomous-Language-Agents
An Open-source Framework for Autonomous Language Agents
LLaMA-Adapter-Fine-tuning-of-LLaMA
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
vllm-Efficient-Memory-Management-for-Large-Language-Model
A high-throughput and memory-efficient inference and serving engine for LLMs
DoLa-Decoding-by-Contrasting-Layers-Large-Language-Models
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
OmniQuant-Omnidirectionally-Calibrated-Quantization-for-Large-Language-Models
OmniQuant is a simple and powerful quantization technique for LLMs.
Point-Bind_Point-LLM-Aligning-3D-with-Multi-modality
Align 3D Point Cloud with Multi-modalities for Large Language Models
modelscope-agent-Building-Customizable-Agent-System-with-LLMs
ModelScope-Agent: An agent framework connecting models in ModelScope with the world
yarn-Efficient-Context-Window-Extension-of-Large-Language-Models
YaRN: Efficient Context Window Extension of Large Language Models
belebele-Massively-Multilingual-NLU-Evaluation
Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.
DenseDiffusion-Training-free-Text-to-Image-Generation
Official Pytorch Implementation of DenseDiffusion (ICCV 2023)
Qwen-VL-multimodal-version-of-the-large-model-series
The official repo of Qwen-VL chat & pretrained large vision language model proposed by Alibaba Cloud.
OmniQuant-quantization-algorithm-for-LLMs
An efficient, accurate, and omnibearing quantization algorithm for LLMs, encompassing both weight-only quantization (W4A16/W3A16/W2A16) and weight-activation quantization (W6A6, W4A4)
Lemur-Pretrained-Large-Language-Models-Balancing-Text-and-Code-Capabilities
Lemur: The State-of-the-art Open Pretrained Large Language Models Balancing Text and Code Capabilities
codellama-family-of-large-language-models-for-code-based-on-Llama-2
Inference code for CodeLlama models
WizardLM-Large-Pre-Trained-Language-Models-to-Follow-Complex-Instructions
Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder and WizardMath
EasyEdit-Knowledge-Editing-Framework-for-Large-Language-Models.
An Easy-to-use Knowledge Editing Framework for LLMs.
FlexFlow-Low-Latency-High-Performance-LLM-Serving
A distributed deep learning framework.
tifa-Text-to-Image-Faithfulness-Evaluation-with-Question-Answering
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
cursive-py-framework-for-interacting-with-LLMs.
✦ The intuitive python LLM framework
Chat-Haruhi-Suzumiya-Anime-Character-in-Reality-via-Large-Language-Model
Chat凉宫春日, 由李鲁鲁, 冷子昂等同学开发的模仿二次元对话的聊天机器人。
QuIP-Quantization-with-Incoherence-Processing
Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
IncognitoPilot-Large-Language-Model-LLM-with-a-Python-interpreter
An AI code interpreter for sensitive data, powered by GPT-4 or Llama 2.