ProjectD-AI / llama_inference
llama inference for tencentpretrain
☆98Updated last year
Alternatives and similar repositories for llama_inference:
Users that are interested in llama_inference are comparing it to the libraries listed below
- ChatGLM-6B fine-tuning.☆135Updated 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
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆106Updated last year
- deep learning☆150Updated 2 weeks ago
- moss chat finetuning☆50Updated 11 months ago
- 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
- ☆306Updated last year
- alpaca中文指令微调数据集☆392Updated 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。☆116Updated 2 weeks ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆132Updated 3 months ago
- 文本去重☆69Updated 10 months ago
- Simple implementation of using lora form the peft library to fine-tune the chatglm-6b☆85Updated last year
- Luotuo Embedding(骆驼嵌入) is a text embedding model, which developed by 李鲁鲁, 冷子昂, 陈启源, 蒟蒻等.☆264Updated last year
- Implementation of Chinese ChatGPT☆287Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆171Updated last year
- pCLUE: 1000000+多任务提示学习数据集☆485Updated 2 years ago
- 骆驼QA,中文大语言阅读理解模型。☆75Updated last year
- (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
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆390Updated last year
- 中文 Instruction tuning datasets☆129Updated 11 months ago
- text embedding☆144Updated last year
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated last year
- 中文图书语料MD5链接☆217Updated last year
- 本项目旨在对大量文本文件进行快速编码检测和转换以辅助mnbvc语料集项目的数据清洗工作☆59Updated 5 months ago
- baichuan LLM surpervised finetune by lora☆62Updated last year
- 基于sentence transformers和chatglm实现的文档搜索工具☆154Updated last year
- 怎么训练一个LLM分词器☆142Updated last year
- ☆172Updated last year
- 纯c++的全平台llm加速库,支持python调用,支持baichuan, glm, llama, moss基座,手机端流畅运行chatglm-6B级模型单卡可达10000+token / s,☆45Updated last year
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆65Updated last year