infinigence / Infini-Megrez
☆310Updated 4 months ago
Alternatives and similar repositories for Infini-Megrez:
Users that are interested in Infini-Megrez are comparing it to the libraries listed below
- ☆225Updated 2 months ago
- GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation☆119Updated this week
- Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent☆310Updated 2 weeks ago
- A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.☆37Updated 4 months ago
- GLM Series Edge Models☆137Updated 2 months ago
- Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.☆232Updated 2 months ago
- FlexRAG: A RAG Framework for Information Retrieval and Generation.☆163Updated last week
- This is a user guide for the MiniCPM and MiniCPM-V series of small language models (SLMs) developed by ModelBest. “面壁小钢炮” focuses on achi…☆235Updated 6 months ago
- ☆239Updated 8 months ago
- 中文Mixtral-8x7B（Chinese-Mixtral-8x7B）☆650Updated 8 months ago
- GPT-4o-level, real-time spoken dialogue system.☆321Updated 3 months ago
- LLM101n: Let's build a Storyteller 中文版☆132Updated 8 months ago
- ☆173Updated 3 months ago
- MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval☆157Updated 3 weeks ago
- 🌐 WebWalker: Benchmarking LLMs in Web Traversal☆390Updated last week
- ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents☆462Updated last month
- Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.☆550Updated 9 months ago
- ☆679Updated 3 weeks ago
- A Toolkit for Running On-device Large Language Models (LLMs) in APP☆72Updated 10 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆633Updated last week
- Collect every awesome work about r1!☆356Updated last week
- 这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。☆379Updated 2 months ago
- 利用免费的大模型api来结合你的私域数据来生成sft训练数据（妥妥白嫖）支持llamafactory等工具的训练数据格式synthetic data☆159Updated 5 months ago
- Repo for NAACL 2025 Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"☆270Updated 3 months ago
- ☆131Updated 2 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆245Updated this week
- ☆59Updated last year
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,110Updated last week
- The plan which extend ChatHaruhi into Zero-shot Roleplaying model☆104Updated last year
- Alpaca Chinese Dataset -- 中文指令微调数据集☆199Updated 7 months ago