Yaowei Zheng's picture

Yaowei Zheng

hiyouga

·

https://github.com/hiyouga

AI & ML interests

LLM Knowledge Management

Recent Activity

liked a dataset 5 days ago

DeL-TaiseiOzaki/Tengentoppa-sft-v1.0

liked a dataset 5 days ago

lmms-lab/LLaVA-OneVision-Data

reacted to davidberenstein1957's post with 🔥 8 days ago

Introducing the Synthetic Data Generator, a user-friendly application that takes a no-code approach to creating custom datasets with Large Language Models (LLMs). The best part: A simple step-by-step process, making dataset creation a non-technical breeze, allowing anyone to create datasets and models in minutes and without any code. Blog: https://huggingface.co/blog/synthetic-data-generator Space: https://huggingface.co/spaces/argilla/synthetic-data-generator

View all activity

Articles

GaLore: Advancing Large Model Training on Consumer-grade Hardware

Organizations

hiyouga's activity

liked 2 datasets 5 days ago

DeL-TaiseiOzaki/Tengentoppa-sft-v1.0

Viewer • Updated 14 days ago • 508k • 1.94k • 21

lmms-lab/LLaVA-OneVision-Data

Viewer • Updated Oct 22 • 3.72M • 12.4k • 149

reacted to davidberenstein1957's post with 🔥 8 days ago

Post

4096

Introducing the Synthetic Data Generator, a user-friendly application that takes a no-code approach to creating custom datasets with Large Language Models (LLMs). The best part: A simple step-by-step process, making dataset creation a non-technical breeze, allowing anyone to create datasets and models in minutes and without any code.

Blog: https://huggingface.co/blog/synthetic-data-generator
Space: argilla/synthetic-data-generator

4 replies

·

upvoted a paper 14 days ago

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Paper • 2412.06559 • Published 15 days ago • 68

liked a model 19 days ago

alpindale/Llama-3.2-11B-Vision-Instruct

Image-Text-to-Text • Updated Sep 25 • 9.1k • 13

upvoted a paper 21 days ago

Yi-Lightning Technical Report

Paper • 2412.01253 • Published 22 days ago • 25

liked a model 27 days ago

Skywork/Skywork-o1-Open-Llama-3.1-8B

Text Generation • Updated 27 days ago • 2.07k • 84

updated a model 27 days ago

hiyouga/Qwen2-VL-7B-Pokemon

Visual Question Answering • Updated 27 days ago • 10 • 9

updated a dataset 27 days ago

llamafactory/OpenO1-SFT

Viewer • Updated 27 days ago • 126k • 193 • 1

liked a dataset 28 days ago

O1-OPEN/OpenO1-SFT

Viewer • Updated 8 days ago • 77.7k • 2.01k • 256

upvoted 2 papers about 1 month ago

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

Paper • 2411.07975 • Published Nov 12 • 27

Hyper-Connections

Paper • 2409.19606 • Published Sep 29 • 20

liked a dataset about 2 months ago

wyu1/Leopard-Instruct

Viewer • Updated Nov 8 • 1.03M • 271k • 51

updated a model about 2 months ago

llamafactory/tiny-random-Llama-3-pissa

New activity in llamafactory/tiny-random-Llama-3-valuehead about 2 months ago

Any chance you could include the value head weights?

#1 opened about 2 months ago by

updated a Space about 2 months ago

LLaMA Board

Fine-tuning large language model with Gradio UI

authored a paper about 2 months ago

EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations

Paper • 2410.10315 • Published Oct 14 • 2

upvoted a paper 2 months ago

LLM-based Optimization of Compound AI Systems: A Survey

Paper • 2410.16392 • Published Oct 21 • 14

liked a model 2 months ago

rhymes-ai/Aria

Image-Text-to-Text • Updated 7 days ago • 18.1k • 599

New activity in Qwen/Qwen2-VL-7B-Instruct 3 months ago

LoRA Finetuning Tool for Qwen2-VL-7B in Web UI (DPO updated)

#2 opened 4 months ago by