Pinned Repositories
alaska
albert_zh
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
baichuan-7B
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
camelot
A Python library to extract tabular data from PDFs
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
Chinese-BERT-wwm
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
DCCToolbox
for dcc lab
DeBERTa
The implementation of DeBERTa
image-caption-ai-challenger2017
image caption based on show attention and tell using tensorflow
hongjian's Repositories
hongjian/albert_zh
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
hongjian/baichuan-7B
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
hongjian/camelot
A Python library to extract tabular data from PDFs
hongjian/ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
hongjian/Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
hongjian/ELLE
hongjian/FinGLM
hongjian/GLM
GLM (General Language Model)
hongjian/GLM-130B
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
hongjian/kaggle-solutions
🏅 Collection of Kaggle Solutions and Ideas 🏅
hongjian/llama
Inference code for LLaMA models
hongjian/llama.cpp
Port of Facebook's LLaMA model in C/C++
hongjian/llama2.c
Inference Llama 2 in one file of pure C
hongjian/MacBERT
Revisiting Pre-trained Models for Chinese Natural Language Processing (MacBERT)
hongjian/metaseq
Repo for external large-scale work
hongjian/MOSS
An open-source tool-augmented conversational language model from Fudan University
hongjian/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
hongjian/pdfminer.six
Community maintained fork of pdfminer - we fathom PDF
hongjian/pdfplumber
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
hongjian/prompt-tuning
Original Implementation of Prompt Tuning from Lester, et al, 2021
hongjian/qlib
Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment. With Qlib, you can easily try your ideas to create better Quant investment strategies. An increasing number of SOTA Quant research works/papers are released in Qlib.
hongjian/roberta_zh
RoBERTa中文预训练模型: RoBERTa for Chinese
hongjian/self-instruct
Aligning pretrained language models with instruction data generated by themselves.
hongjian/sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
hongjian/simclr
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
hongjian/SimCSE
EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings
hongjian/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
hongjian/t5-pegasus
中文生成式预训练模型
hongjian/tabula
Tabula is a tool for liberating data tables trapped inside PDF files
hongjian/tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.