CoinCheung / gdGPT

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

Add bisenetv2. My implementation of BiSeNet

mIOU=80.02 on cityscapes. My implementation of deeplabv3+ (also know as 'Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation' based on the dataset of cityscapes).

a 2048 small game writen by python and c

#大语言模型#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

#大语言模型#The blog, read report and code example for AGI/LLM related knowledge.

#大语言模型#LLaVA是一个具有 GPT-4V 级别功能的大语言和视觉模型助手

#自然语言处理#收集和梳理垂直领域的开源模型、数据集及评测基准。

Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)

Go ahead and axolotl questions

#大语言模型#Code examples and resources for DBRX, a large language model developed by Databricks

The personal finance app for everyone

Open-Sora： 完全开源的高效复现类Sora视频生成方案

"他山之石、可以攻玉"：复旦白泽智能发布面向国内开源和国外商用大模型的Demo数据集JADE-DB

RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.

Minimalistic large language model 3D-parallelism training

Window management made elegant.