lili0710432's repositories
LLaMA-Adapter
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
FinanceChatGLM
SMP 2023 ChatGLM金融大模型挑战赛 60 分baseline思路介绍
kaggle-solutions
🏅 Collection of Kaggle Solutions and Ideas 🏅
text2vec
text2vec, text to vector. 文本向量表征工具,把文本转化为向量矩阵,实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型,开箱即用。
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain | 基于本地知识库的 ChatGLM 问答
fastllm
纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.
mPLUG-Owl
mPLUG-Owl🦉: Modularization Empowers Large Language Models with Multimodality
ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
llmtune
4-Bit Finetuning of Large Language Models on One Consumer GPU
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
gpt4all
gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
BELLE
BELLE: Be Everyone's Large Language model Engine(开源中文对话大模型)
Fengshenbang-LM
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系,成为中文AIGC和认知智能的基础设施。
llama
Inference code for LLaMA models
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
nebula-algorithm
Nebula-Algorithm is a Spark Application based on GraphX, which enables state of art Graph Algorithms to run on top of NebulaGraph and write back results to NebulaGraph.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
chatgpt-comparison-detection
Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥
GraphSAGE
Implement GraphSAGE with Python, PyTorch Geometric
cnsenti
中文情感分析库(Chinese Sentiment))可对文本进行情绪分析、正负情感分析。Chinese sentiment analysis library, which supports counting the number of different emotional words in the text
RL-Stock
📈 如何用深度强化学习自动炒股
PromptInject
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022
PLOME
Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021
Adversarial-Train
NLP对抗训练,包括PGD、FGM、FGSM、FreeAT