iflytek / VLE
VLE: Vision-Language Encoder (VLE: 视觉-语言多模态预训练模型)
☆190Updated 2 years ago
Alternatives and similar repositories for VLE:
Users that are interested in VLE are comparing it to the libraries listed below
- transformers结构的中文OFA模型☆130Updated 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。☆370Updated last year
- chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu☆164Updated last year
- A Chinese Open-Domain Dialogue System☆321Updated last year
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆390Updated 2 years ago
- MiniRBT (中文小型预训练模型系列)☆276Updated 2 years ago
- Baichuan-13B 指令微调☆89Updated last year
- 语言模型中文认知能力分析☆236Updated last year
- ChatGLM-6B fine-tuning.☆135Updated 2 years ago
- Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.☆167Updated 2 years ago
- deep learning☆149Updated last month
- llama inference for tencentpretrain☆98Updated last year
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆398Updated 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.☆250Updated last year
- baichuan LLM surpervised finetune by lora☆63Updated 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☆410Updated last year
- ☆308Updated 2 years ago
- Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM☆100Updated 11 months ago
- pCLUE: 1000000+多任务提示学习数据集☆490Updated 2 years ago
- 中文CLIP预训练模型☆410Updated 2 years ago
- alpaca中文指令微调数据集☆392Updated 2 years ago
- ☆278Updated last year
- 中文聊天小模型,用t5 base在大量数据上有监督。☆101Updated last year
- Implementation of Chinese ChatGPT☆287Updated last year
- X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages☆310Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆654Updated 2 years ago
- chatglm多gpu用deepspeed和☆409Updated 9 months ago
- 多模态中文LLaMA&Alpaca大语言模型(VisualCLA)☆445Updated last year
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆192Updated last year
- 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)。☆359Updated last year