supersymmetry-technologies / BBT-FinCUGE-ApplicationsLinks
☆276Updated 2 years ago
Alternatives and similar repositories for BBT-FinCUGE-Applications
Users that are interested in BBT-FinCUGE-Applications are comparing it to the libraries listed below
Sorting:
- FinEval是一个中文金融领域高质量多项选择与文本问答题的集合。☆238Updated 4 months ago
- ☆244Updated last year
- DISC-FinLLM,中文金融大语言模型(LLM),旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide us…☆801Updated 2 years ago
- 聚宝盆(Cornucopia): 中文金融系列开源可商用大模型,并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)☆648Updated 2 years ago
- SMP 2023 ChatGLM金融大模型挑战赛 60 分baseline思路介绍☆186Updated 2 years ago
- 语言模型中文认知能力分析☆237Updated 2 years ago
- change pdf to txt☆67Updated 2 years ago
- Baichuan2代码的逐行解析版本,适合小白☆214Updated 2 years ago
- ☆194Updated 9 months ago
- ☆72Updated 11 months ago
- ☆84Updated 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
- ☆164Updated 2 years ago
- 国内首个全参数训练的法律大模型 HanFei-1.0 (韩非)☆124Updated 2 years ago
- 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 2 years ago
- 开源SFT数据集整理,随时补充☆557Updated 2 years ago
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆262Updated 11 months ago
- 活字通用大模型☆391Updated last year
- deep learning☆148Updated 6 months ago
- ☆532Updated last year
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆401Updated 2 years ago
- ☆356Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆178Updated 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)。☆356Updated 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☆196Updated 2 years ago
- PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese☆381Updated last year
- Baichuan-13B 指令微调☆90Updated 2 years ago
- 雅意信息抽取大模型:在百万级人工构造的高质量信息抽取数据上进行指令微调,由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)☆313Updated last year
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆285Updated last year
- 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。☆220Updated last year