zlh1992's repositories
BigLlamaTuningSummary
Tuning Llama Models > 7b
multilabel-classification
Multilabel classification using BERT embeddings
SimCSE-Pytorch
中文数据集下SimCSE+ESimCSE的实现
alpaca-lora
Instruct-tune LLaMA on consumer hardware
autogluon
AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data
BELLE
BELLE: Be Everyone's Large Language model Engine(开源中文对话大模型)
ChatGPTX-Uni
实现一种单/多Lora-Fusion权值交叉融合+Zero-Finetune零微调增强的跨模型技术方案,LLM-Base+LLM-X+Alpaca,初期,LLM-Base为Chatglm6B底座模型,LLM-X是LLAMA增强模型。该方案简易高效,目标是使此类语言模型能够低能耗广泛部署,并最终在小模型的基座上发生“智能涌现”,力图最小计算代价达成ChatGPT、GPT4、ChatRWKV等人类友好亲和效果。后期将以此为中心模型大脑Agent,进一步融入并指挥CV目标检测、文本图像生成、语音命令交互等执行模型。当前可以满足总结、提问、问答、摘要、改写、评论、扮演等各种需求。
chatyuan_finetuning
clue chatyuan finetuning
Chinese-alpaca-lora
骆驼:A Chinese finetuned instruction LLaMA. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技
ColossalAI
Making big AI models cheaper, easier, and scalable
colossalAI_study
个人改进与学习
gluonts
Probabilistic time series modeling in Python
GPTQ-for-LLaMa
4 bits quantization of LLaMa using GPTQ
greykite
A flexible, intuitive and fast forecasting library
HLATR
Implementation of paper: HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking
human-eval
Code for the paper "Evaluating Large Language Models Trained on Code"
KDDCup2022-ESCI
Oral presentation at KDD Cup Workshop @ KDD 2022
llama
Inference code for LLaMA models
LOMO
LOMO: LOw-Memory Optimization
mm-cot
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
NBCE
Naive Bayes-based Context Extension
neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
py-tree-sitter
Python bindings to the Tree-sitter parsing library
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.