thunlp / Delta-CoMeLinks
Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024
☆56Updated 9 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:
- Mixture-of-Experts (MoE) Language Model☆189Updated 11 months ago
- GLM Series Edge Models☆147Updated 2 months ago
- ☆94Updated 8 months ago
- a toolkit on knowledge distillation for large language models☆141Updated this week
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆136Updated last year
- [ACL 2025] An official pytorch implement of the paper: Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement☆34Updated 2 months ago
- Qwen DianJin: LLMs for the Financial Industry by Alibaba Cloud☆135Updated 2 weeks ago
- ☆290Updated 2 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 3 months ago
- Its an open source LLM based on MOE Structure.☆58Updated 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。☆43Updated 6 months ago
- ☆67Updated 2 months ago
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆33Updated last year
- SUS-Chat: Instruction tuning done right☆49Updated last year
- Deep Reasoning Translation (DRT) Project☆227Updated 2 months ago
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆141Updated last year
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆41Updated last year
- The RedStone repository includes code for preparing extensive datasets used in training large language models.☆137Updated last month
- ☆103Updated 2 months ago
- ☆79Updated 4 months ago
- ☆40Updated last year
- Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"☆140Updated 2 months ago
- Ling is a MoE LLM provided and open-sourced by InclusionAI.☆187Updated 3 months ago
- XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.☆40Updated last year
- FuseAI Project☆87Updated 6 months ago
- ☆231Updated last year
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆188Updated 2 months ago
- Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414☆303Updated last week
- ☆63Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year