TylunasLi / fastllm
纯c++的全平台llm加速库,支持python调用,支持chatglm-6B, llama, baichuan, moss基座,x86 / ARM
☆9Updated last month
Alternatives and similar repositories for fastllm:
Users that are interested in fastllm are comparing it to the libraries listed below
- accelerate generating vector by using onnx model☆13Updated last year
- 介绍docker、docker compose的使用。☆20Updated 4 months ago
- ☆37Updated 9 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆127Updated last month
- (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
- 打造人人都会的NLP,开源不易,记得star哦☆100Updated last year
- Zero-human, cold-start construction of long-chain agents in professional domains☆22Updated 2 weeks ago
- qwen-7b and qwen-14b finetuning☆88Updated 9 months ago
- share data, prompt data , pretraining data☆35Updated last year
- Imitate OpenAI with Local Models☆85Updated 5 months ago
- ☆49Updated 5 months ago
- NLP 项目记录档案☆51Updated last week
- Python3 package for Chinese/English OCR, with paddleocr-v4 onnx model(~14MB). 基于ppocr-v4-onnx模型推理,可实现 CPU 上毫秒级的 OCR 精准预测,通用场景中英文OCR达到开源SO…☆54Updated last week
- 骆驼QA,中文大语言阅读理解模型。☆74Updated last year
- 使用langchain进行任务规划,构建子任务的会话场景资源,通过MCTS任务执行器,来让每个子任务通过在上下文中资源,通过自身反思探索来获取自身对问题的最优答案;这种方式依赖模型的对齐偏好,我们在每种偏好上设计了一个工程框架,来完成自我对不同答案的奖励进行采样策略☆22Updated this week
- 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
- ☆114Updated 8 months ago
- the newest version of llama3,source code explained line by line using Chinese☆22Updated 9 months ago
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆76Updated 8 months ago
- 智谱AI 2024年金融行业大模型挑战赛仓库☆35Updated last month
- 本项目基于modelscope-agent-v0.3和 api-for-open-llm 或 llamacpp 组件共同实现了一个AI Agent,能够利用本地的大模型(LLM)实现使用自定义工具功能。使用了Qwen1.5大模型。☆14Updated 9 months ago
- 专注于对话系统领域的技术分享,重点写《Dify应用操作和源码剖析》专栏。☆71Updated 6 months ago
- pretrain a wiki llm using transformers☆20Updated 4 months ago
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated last year
- bge推理优化相关脚本☆27Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆105Updated last year
- aigc_serving lightweight and efficient Language service model reasoning☆24Updated 7 months ago
- ☆15Updated 7 months ago
- 大语言模型应用:RAG、NL2SQL、聊天机器人、预训练、MOE混合专家模型、微调训练、强化学习、天池数据竞赛☆53Updated last month
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Updated 9 months ago