infinigence / InfiniWebSearchLinks
A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.
☆39Updated last year
Alternatives and similar repositories for InfiniWebSearch
Users that are interested in InfiniWebSearch are comparing it to the libraries listed below
Sorting:
- Its an open source LLM based on MOE Structure.☆58Updated last year
- A dataset template for guiding chat-models to self-cognition, including information about the model’s identity, capabilities, usage, limi…☆30Updated 2 years ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆140Updated last year
- ☆235Updated last year
- Imitate OpenAI with Local Models☆89Updated last year
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆141Updated last year
- ☆174Updated last year
- The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"☆266Updated last year
- 首个llama2 13b 中文版模型 (Base + 中文对话SFT,实现流畅多轮人机自然语言交互)☆91Updated 2 years ago
- 中文原生检索增强生成测评基准☆122Updated last year
- (撰写ing..)本仓库偏教程性质,以「模型中文化」为一个典型的模型训练问题切入场景,指导读者上手学习LLM二次微调训练。☆36Updated last year
- GLM Series Edge Models☆156Updated 7 months ago
- gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR、TTS、文生图、图片编辑和文生视频的开源框架。☆243Updated 2 weeks ago
- 中文基于满血DeepSeek-R1蒸馏数据集☆63Updated 10 months ago
- NLP 项目记录档案☆61Updated 8 months ago
- Alpaca Chinese Dataset -- 中文指令微调数据集☆217Updated last year
- code for piccolo embedding model from SenseTime☆144Updated last year
- 基于langchain设计的智能体任务,包含规划会话场景资源,构建子任务,任务执行器包含(MCTS)☆32Updated 2 months ago
- 360zhinao☆291Updated 7 months ago
- Mixture-of-Experts (MoE) Language Model☆192Updated last year
- SearchGPT: Building a quick conversation-based search engine with LLMs.☆46Updated last year
- ☆341Updated 3 months ago
- llama inference for tencentpretrain☆99Updated 2 years ago
- 大语言模型指令调优工具(支持 FlashAttention)☆178Updated 2 years ago
- 文本去重☆77Updated last year
- 我们是第一个完全可商用的角色大模型。☆40Updated last year
- a toolkit on knowledge distillation for large language models☆237Updated 2 weeks ago
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆59Updated last year
- deep learning☆149Updated 8 months ago
- ☆106Updated 2 years ago