ztxz16 / fastllmLinks
fastllm是c++实现，后端无依赖（仅依赖CUDA，无需依赖PyTorch）的高性能大模型推理库。 可实现单4090推理DeepSeek R1 671B INT4模型，单路可达20+tps。
☆3,574Updated last week
Alternatives and similar repositories for fastllm
Users that are interested in fastllm are comparing it to the libraries listed below
Sorting:
- C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)☆2,975Updated 10 months ago
- Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调☆3,704Updated last year
- Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集☆3,056Updated last year
- llm deploy project based mnn. This project has merged into MNN.☆1,581Updated 4 months ago
- A series of large language models developed by Baichuan Intelligent Technology☆4,124Updated 6 months ago
- A large-scale 7B pretraining language model developed by BaiChuan-Inc.☆5,685Updated 10 months ago
- 基于ChatGLM-6B + LoRA的Fintune方案☆3,765Updated last year
- A 13B large language model developed by Baichuan Intelligent Technology☆2,970Updated last year
- 计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点☆2,425Updated 3 months ago
- Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、…☆6,420Updated 7 months ago
- TigerBot: A multi-language multi-task LLM☆2,257Updated 5 months ago
- Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca☆4,156Updated last month
- Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型☆4,155Updated 9 months ago
- BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）☆8,164Updated 7 months ago
- 中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)☆7,159Updated 8 months ago
- 开源社区第一个能下载、能运行的中文 LLaMA2 模型！☆2,232Updated last year
- Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, X…☆2,438Updated 8 months ago
- 基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等☆2,749Updated last year
- chatglm 6b finetuning and alpaca finetuning☆1,543Updated 2 months ago
- ChatGPT爆火，开启了通往AGI的关键一步，本项目旨在汇总那些ChatGPT的开源平替们，包括文本大模型、多模态大模型等，为大家提供一些便利☆2,038Updated last year
- 骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技☆3,637Updated last year
- 闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题☆6,245Updated 4 months ago
- a lightweight LLM model inference framework☆728Updated last year
- MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志…☆3,868Updated last month
- Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]☆1,736Updated last year
- ChatYuan: Large Language Model for Dialogue in Chinese and English☆1,889Updated last year
- 人工精调的中文对话数据集和一段chatglm的微调代码☆1,178Updated 3 weeks ago
- GLM (General Language Model)☆3,239Updated last year
- WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)☆1,594Updated 2 months ago
- We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tunin…☆2,747Updated last year