Macielyoung / Chinese-Image-CaptionLinks
Train a model for Image Caption from ViT and GPT pretrained model
☆18Updated 2 years ago
Alternatives and similar repositories for Chinese-Image-Caption
Users that are interested in Chinese-Image-Caption are comparing it to the libraries listed below
Sorting:
- transformers结构的中文OFA模型☆135Updated 2 years ago
- Baichuan-13B 指令微调☆90Updated 2 years ago
- baichuan LLM surpervised finetune by lora☆64Updated 2 years ago
- 使用sentencepiece中BPE训练中文词表,并在transformers中进行使用。☆119Updated 2 years ago
- VLE: Vision-Language Encoder (VLE: 视觉-语言多模态预训练模型)☆194Updated 2 years ago
- 支持中英文双语视觉-文本对话的开源可商用多模态模型。☆376Updated 2 years ago
- 大语言模型指令调优工具(支持 FlashAttention)☆178Updated last year
- Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.☆169Updated 2 years ago
- ☆167Updated last year
- 基于ClipCap的看图说话Image Caption模型☆315Updated 3 years ago
- 中文CLIP预训练模型☆417Updated 2 years ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆110Updated 2 years ago
- ☆66Updated last year
- 用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.☆254Updated 2 years ago
- MiniRBT (中文小型预训练模型系列)☆295Updated 2 months ago
- ChatGLM-6B fine-tuning.☆136Updated 2 years ago
- 多轮共情对话模型PICA☆97Updated 2 years ago
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆401Updated 2 years ago
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆344Updated last year
- ☆74Updated last year
- ☆118Updated last year
- 专注于中文领域大语言模型,落地到某个行业某个领域,成为一个行业大模型、公司级别或行业级别领域大模型。☆123Updated 7 months ago
- A Chinese Open-Domain Dialogue System☆324Updated 2 years ago
- chatglm多gpu用deepspeed和☆412Updated last year
- Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆413Updated last year
- qwen models finetuning☆104Updated 7 months ago
- 多模态中文LLaMA&Alpaca大语言模型(VisualCLA)☆453Updated 2 years ago
- 中文 Instruction tuning datasets☆136Updated last year
- kbqa,langchain,large langauge model, chatgpt☆81Updated 11 months ago
- ☆308Updated 2 years ago