Baiph's starred repositories
DeepSeek-Coder-V2
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
BankOCRMoE
第四届厦门国际银行数创金融杯建模大赛冠军方案(含OCR预训练权重)
CALNet-Dronevehicle
[ACM MM 2023 Oral] Multispectral Object Detection via Cross-Modal Conflict-Aware Learning.
Vehicle-Detection
Vehicle Detection Using Deep Learning and YOLO Algorithm
Awesome-RGBT-Fusion
A collection of deep learning based RGB-T-Fusion methods, codes, and datasets. The main directions involved are Multispectral Pedestrian Detection, RGB-T Aerial Object Detection, RGB-T Semantic Segmentation, RGB-T Crowd Counting, RGB-T Fusion Tracking.
VIF-Benchmark
All deep learning-based infrared and visible image fusion algorithms in a whole framework
kaggle-feedback-english-language-learning-1st-place-solution
Feedback Prize - English Language Learning: 1st place solution code
ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
chatGLM-6B-QLoRA
使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。
LLM-Tuning
Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.
ChatGLM-Finetuning
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
Tianchi-LLM-retrieval
2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答, 75+ baseline
kaggle-feedback-effectiveness-1st-place-solution
Winning solution for the Kaggle Feedback Prize Challenge.