thunlp / Delta-CoMeLinks
Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024
☆57Updated 6 months ago
Alternatives and similar repositories for Delta-CoMe
Users that are interested in Delta-CoMe are comparing it to the libraries listed below
Sorting:
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆132Updated 11 months ago
- Mixture-of-Experts (MoE) Language Model☆188Updated 8 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆166Updated last week
- ☆150Updated last month
- ☆40Updated last year
- FuseAI Project☆87Updated 4 months ago
- ☆94Updated 5 months ago
- An Open Math Pre-trainng Dataset with 370B Tokens.☆87Updated last month
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆56Updated last year
- GLM Series Edge Models☆141Updated 3 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory☆95Updated last month
- A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.☆38Updated 5 months ago
- Qwen DianJin: LLMs for the Financial Industry by Alibaba Cloud☆105Updated last week
- ☆223Updated this week
- ☆228Updated last year
- ☆47Updated 11 months ago
- [ACL 2025] An official pytorch implement of the paper: Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement☆27Updated this week
- ☆80Updated 2 weeks ago
- Ling is a MoE LLM provided and open-sourced by InclusionAI.☆157Updated 2 weeks ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆101Updated 2 weeks ago
- ☆82Updated last year
- SUS-Chat: Instruction tuning done right☆48Updated last year
- Its an open source LLM based on MOE Structure.☆58Updated 11 months ago
- zero零训练llm调参☆31Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- 最简易的R1结果在小模型上的复现,阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证,对于强推理能力,think思考过程性内容是AGI/ASI的核心。☆45Updated 3 months ago
- Light local website for displaying performances from different chat models.☆86Updated last year
- [ICML2025] The official implementation of "C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Gene…☆22Updated last month
- ☆188Updated last month
- the newest version of llama3,source code explained line by line using Chinese☆22Updated last year