yongzhuo / ChatGLM2-SFT
ChatGLM2-6B微调, SFT/LoRA, instruction finetune
☆106Updated last year
Related projects ⓘ
Alternatives and complementary repositories for ChatGLM2-SFT
- 使用qlora对中文大语言模型进行微调,包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆85Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆166Updated 10 months ago
- 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。☆111Updated last month
- chatglm2 6b finetuning and alpaca finetuning☆144Updated 6 months ago
- (1)弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练,提高万级tokens性能支持。(2)证据理论解释学习,提升模型的复杂逻辑推理能力(3)兼容alpaca数据格式。☆45Updated last year
- baichuan LLM surpervised finetune by lora☆60Updated 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☆163Updated last year
- GoGPT:基于Llama/Llama 2训练的中英文增强大模型|Chinese-Llama2☆78Updated last year
- moss chat finetuning☆50Updated 6 months ago
- ☆157Updated last year
- Baichuan-13B 指令微调☆89Updated last year
- deepspeed+trainer简单高效实现多卡微调大模型☆116Updated last year
- ChatGLM-6B fine-tuning.☆135Updated last year
- 骆驼QA,中文大语言阅读理解模型。☆72Updated last year
- 怎么训练一个LLM分词器☆129Updated last year
- llama inference for tencentpretrain☆96Updated 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。☆202Updated 11 months ago
- 支持ChatGLM2 lora微调☆39Updated last year
- 实现了Baichuan-Chat微调,Lora、QLora等各种微调方式,一键运行。☆71Updated last year
- deep learning☆148Updated 4 months ago
- basic framework for rag(retrieval augment generation)☆75Updated 10 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆121Updated 10 months ago
- qwen-7b and qwen-14b finetuning☆82Updated 6 months ago
- Baichuan2代码的逐行解析版本,适合小白☆209Updated last year
- 中文 Instruction tuning datasets☆118Updated 7 months ago
- 中文原生检索增强生成测评基准☆98Updated 6 months ago
- Finetune baichuan pretrained model with QLora method☆15Updated last year
- 中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…☆166Updated 5 months ago
- LLM for NER☆54Updated 3 months ago