Skip to content
View terminator123's full-sized avatar

Block or report terminator123

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

LLM KV cache compression made easy

Python 1,091 147 Updated May 18, 2026

总结Prompt&LLM论文,开源数据&模型,AIGC应用

3,408 322 Updated May 6, 2026
Python 186 3 Updated Jan 19, 2026

《How to Scale Your Model》中文翻译项目 - 智能技术文档翻译工具。专为大语言模型扩展技术书籍设计,突破长文档翻译瓶颈,完美保留数学公式、代码块格式。采用占位符机制+分层翻译策略,基于Gemini API提供高质量翻译。Python+crawl4ai技术栈,支持批量处理和增量更新。

HTML 167 16 Updated Aug 30, 2025

Efficient Triton Kernels for LLM Training

Python 6,382 532 Updated May 25, 2026

AIInfra(AI 基础设施)指AI系统从底层芯片等硬件,到上层软件栈支持AI大模型训练和推理。

Jupyter Notebook 7,118 916 Updated Dec 22, 2025

Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.

Python 192 32 Updated May 20, 2026

how to optimize some algorithm in cuda.

Cuda 3,021 277 Updated May 25, 2026

Machine Learning Engineering Open Book

Python 17,980 1,140 Updated May 18, 2026

PyTorch native post-training library

Python 5,760 723 Updated May 25, 2026

Pipeline Parallelism Emulation and Visualization

Python 83 9 Updated Jan 8, 2026

a static analytical model for LLM distributed training

Python 133 19 Updated May 11, 2026

Zero Bubble Pipeline Parallelism

Python 456 34 Updated May 7, 2025

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

7,999 288 Updated May 15, 2025
Jupyter Notebook 9 5 Updated Nov 5, 2024

Firefly: 大模型训练工具,支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

Python 6,643 586 Updated Oct 24, 2024

This is the repo for the survey of LLM4IR.

535 44 Updated Nov 13, 2025

深度学习经典、新论文逐段精读

33,330 2,803 Updated Mar 22, 2025

使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。

Python 358 45 Updated Aug 22, 2023

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等

Python 2,778 308 Updated Dec 12, 2023

This repo was a simple way to implement Lora to fine-tuning ChatGLM2.这个项目是用LORA微调chatglm2的简单实现。

Python 9 1 Updated Aug 21, 2023

CCL2019,“小牛杯”中文幽默计算任务的数据集及baseline

Jupyter Notebook 25 4 Updated Aug 27, 2024

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化,也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

4,199 288 Updated May 23, 2026

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

Python 1,604 134 Updated Mar 25, 2025

Pytorch-Named-Entity-Recognition-with-BERT

Python 1,249 271 Updated May 6, 2021

An open source implementation of CLIP.

Python 13,855 1,283 Updated May 25, 2026

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

9,893 1,555 Updated Feb 6, 2026

非常全的古诗词数据,收录了从先秦到现代的共计85万余首古诗词。

Python 1,735 417 Updated Aug 8, 2023
Next