ma La

schrecke1337

AI & ML interests

None yet

Recent Activity

liked a model 8 days ago

cerebras/Qwen3-Coder-REAP-25B-A3B

liked a model 2 months ago

huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated

liked a model 3 months ago

ServiceNow-AI/Apriel-1.5-15b-Thinker

View all activity

Organizations

None yet

liked a model 8 days ago

cerebras/Qwen3-Coder-REAP-25B-A3B

Text Generation • Updated Oct 20 • 54.6k • 63

liked a model 2 months ago

huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated

Image-Text-to-Text • 31B • Updated 13 days ago • 10.2k • 73

liked 2 models 3 months ago

ServiceNow-AI/Apriel-1.5-15b-Thinker

Image-Text-to-Text • 15B • Updated Oct 6 • 7.42k • 460

nvidia/Phi-4-reasoning-plus-NVFP4

8B • Updated Sep 5 • 494 • 6

reacted to MonsterMMORPG's post with 🚀 4 months ago

Post

2420

Huge updates made for SECourses Musubi Tuner - 1-Click to Install App for LoRA Training and Full Fine Tuning Qwen Image, Qwen Image Edit, Wan 2.1 and Wan 2.2 Models with Musubi Tuner with Ready Presets

1-Click to install app link : https://www.patreon.com/posts/137551634

Check all the screenshots

30 August 2025 Update V7
Dataset TOML file generate error fixed

Qwen2.5-VL image captioning turns out working perfect on Windows

It turns out my model file was corrupted even though it was same size

Therefore I have updated the model downloader and now it will check and verify SHA 256 of files therefore it will be 100% accurate

Prompt file selection folder icon issue fixed

Downloader file will use generated venv of installation

Make sure to run it after installation completed

Fixed skip existing captions functionality in Image Captioning with Qwen2.5-VL

Previously skipping was happening after caption generation which was destroying the skip logic

Now properly checks for existing captions before processing, significantly improving efficiency

Added full batch captioning status display in command line with progress tracking and ETA

Enhanced config save/load functionality for better reliability

Improved interface of Image Captioning with Qwen2.5-VL for better user experience

Various error fixes in the Qwen2.5-VL captioning pipeline

Fixed broken config save and load functionality for Optimizer Arguments and Scheduler Arguments

Improved Stop Training button responsiveness - now appears much earlier when Text Encoder caching starts

Enhanced training control for better user experience

A new full dedicated section for Sample generation implemented

It will automatically format your given sample txt file with the settings you set on GUI

So you just type prompts into txt file with new lines e.g.

ohwx man wearing a very nice amazing suit

ohwx man driving a luxury car