KunWang's starred repositories
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
transformers_tasks
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
Counterfactual-DR
The official repository for 'Implicit Feedback for Dense Passage Retrieval: A Counterfactual Approach', Shengyao Zhuang, Hang Li and Guido Zuccon, SIGIR2022
query_variation_generators
Code for the ECIR'22 paper "Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators"
stockManager
An easy way to manage your stock information
Chinese-LLaMA-Alpaca-2
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
prompt-tuning
Original Implementation of Prompt Tuning from Lester, et al, 2021
model-soups
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Channel-LM-Prompting
An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"
c-binance-futures-quant
low-cost, high-efficiency, easy-to-implement
KNNPrompting
Released code for our ICLR23 paper.
direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)