thunlp / Delta-CoMeLinks
Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024
☆57Updated 8 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 10 months ago
- GLM Series Edge Models☆144Updated last month
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆136Updated last year
- ☆94Updated 7 months ago
- XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.☆40Updated 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。☆44Updated 5 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆110Updated 2 months ago
- ☆287Updated 2 months ago
- SUS-Chat: Instruction tuning done right☆49Updated last year
- Qwen DianJin: LLMs for the Financial Industry by Alibaba Cloud☆119Updated 2 months ago
- a toolkit on knowledge distillation for large language models☆127Updated this week
- [ACL 2025] An official pytorch implement of the paper: Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement☆32Updated 2 months ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆40Updated last year
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆33Updated last year
- A Toolkit for Running On-device Large Language Models (LLMs) in APP☆77Updated last year
- ☆77Updated 3 months ago
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆139Updated last year
- Ling is a MoE LLM provided and open-sourced by InclusionAI.☆181Updated 2 months ago
- ☆66Updated 2 months ago
- ☆173Updated 5 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- Its an open source LLM based on MOE Structure.☆58Updated last year
- ☆48Updated last year
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory☆164Updated 2 weeks ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆181Updated last month
- Scaling Preference Data Curation via Human-AI Synergy☆94Updated 3 weeks ago
- ☆157Updated 3 months ago
- Our 2nd-gen LMM☆34Updated last year
- Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"☆136Updated 2 months ago
- XVERSE-MoE-A36B: A multilingual large language model developed by XVERSE Technology Inc.☆39Updated 10 months ago