core-power / Chinese_Chat_T5_BaseLinks
中文聊天小模型,用t5 base在大量数据上有监督。
☆100Updated last year
Alternatives and similar repositories for Chinese_Chat_T5_Base
Users that are interested in Chinese_Chat_T5_Base are comparing it to the libraries listed below
Sorting:
- ChatGLM-6B fine-tuning.☆135Updated 2 years ago
- 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
- baichuan LLM surpervised finetune by lora☆63Updated 2 years ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆108Updated 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。☆118Updated 3 months ago
- pCLUE: 1000000+多任务提示学习数据集☆496Updated 2 years ago
- 使用qlora对中文大语言模型进行微调,包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆87Updated 2 years ago
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测,低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆216Updated last year
- CamelBell(驼铃) is be a Chinese Language Tuning project based on LoRA. CamelBell is belongs to Project Luotuo(骆驼), an open sourced Chinese-…☆174Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆173Updated last year
- Baichuan-13B 指令微调☆90Updated 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.☆252Updated last year
- llama inference for tencentpretrain☆98Updated 2 years ago
- 实现一种多Lora权值集成切换+Zero-Finetune零微调增强的跨模型技术方案,LLM-Base+LLM-X+Alpaca,初期,LLM-Base为Chatglm6B底座模型,LLM-X是LLAMA增强模型。该方案简易高效,目标是使此类语言模型能够低能耗广泛部署,并最…☆115Updated last year
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆390Updated 2 years ago
- Implementation of Chinese ChatGPT☆285Updated last year
- 3000000+语义理解与匹配数据集。可用于无监督对比学习、半监督学习等构建中文领域效果最好的预训练模型☆298Updated 2 years ago
- alpaca中文指令微调数据集☆391Updated 2 years ago
- chatglm多gpu用deepspeed和☆409Updated 11 months ago
- 基于sentence transformers和chatglm实现的文档搜索工具☆156Updated 2 years ago
- A framework for cleaning Chinese dialog data☆271Updated 4 years ago
- dialogbot, provide search-based dialogue, task-based dialogue and generative dialogue model. 对话机器人,基于问答型对话、任务型对话、聊天型对话等模型实现,支持网络检索问答,领域知识…☆333Updated last year
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆399Updated last year
- ☆307Updated 2 years ago
- 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)。☆360Updated last year
- deep learning☆148Updated last month
- 骆驼QA,中文大语言阅读理解模型。☆74Updated 2 years ago
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆195Updated 2 years ago
- NLU & NLG (zero-shot) depend on mengzi-t5-base-mt pretrained model☆74Updated 2 years ago
- moss chat finetuning☆50Updated last year