Friedrich Marty

Smorty100

https://gitlab.com/users/Marty_Friedrich/projects

AI & ML interests

I'm most interested in content rerouting between LLM and VLLM agens for automation possibilities. Using templates for each agent which is then filled in by another agents inputs seems really useful.

Recent Activity

reacted to etemiz's post with 😎 about 13 hours ago

Updated the Hoopoe model which is taking faith related and religious texts in. https://huggingface.co/etemiz/Hoopoe-8B-Llama-3.1 Faith score went from 8% to 54%. Expect more updates and increase in the score. I also did the instruct fine tuning before adding faith to the model. So some of the improvements may be there because I started with llama 3.1 base and not the instruct. Here are some comparisons with original Llama 3.1:

reacted to etemiz's post with 👀 about 13 hours ago

replied to MonsterMMORPG's post 7 days ago

It is now possible to generate 16 Megapixel (4096x4096) raw images with SANA 4K model using under 8GB VRAM, 4 Megapixel (2048x2048) images using under 6GB VRAM, and 1 Megapixel (1024x1024) images using under 4GB VRAM thanks to new optimizations 13 January 2024 Update Installers : https://www.patreon.com/posts/from-nvidia-labs-116474081 New 4K Tutorial Video : https://youtu.be/GjENQfHF4W8 Now the APP will use Diffusers Pipeline and it has huge VRAM optimizations You need to reinstall The models will be downloaded into your Hugging Face cache folder when you first time generate something How to Get Installation Logs and How to Change Hugging Face Cache Folder : https://www.patreon.com/posts/108419878 Please make a fresh install When you enable all 4 optimizations the VRAM usages are like below Make sure shared VRAM is enabled because initial loading of the model need more VRAM Enable VAE Tiling + Enable VAE Slicing + Enable Model CPU Offload + Enable Sequential CPU Offload 1K (1024x1024) : 4 GB GPUs 2K (2048x2048) : 6 GB GPUs 4K (4096x4096) : 8 GB GPUs Still in any case may work on your GPU test it Just Enable VAE Tiling + Enable Model CPU Offload works great in many cases All below attached images are generated via SANA 4K model, they are RAW and their resolution is 5376x3072 Official repo page : https://github.com/NVlabs/Sana

View all activity

Organizations

None yet

Smorty100's activity

New activity in nvidia/Cosmos-NeMo-Assets 12 days ago

Video 4 has rapid snapping movements during the end of the video

#2 opened 12 days ago by

Smorty100

New activity in ise-uiuc/Magicoder-S-DS-6.7B 17 days ago

AMAZING CODING MODEL!!!

#1 opened about 1 year ago by

rombodawg

New activity in huggingchat/chat-ui 17 days ago

Every model is going nuts now

#647 opened 17 days ago by

sneedingface

New activity in huggingchat/chat-ui 19 days ago

Your feedback on HuggingChat

265

#1 opened over 1 year ago by

victor

New activity in cfahlgren1/react-code-instructions 19 days ago

Potential bad generations cannot be labeled in the Deepseek Artifacts UI, dislike button would be appreciated

#2 opened 19 days ago by

Smorty100

New activity in huggingchat/chat-ui 21 days ago

Please add newer models (deepseek v3)

#645 opened 23 days ago by

Someone2077

[MODELS] Discussion

566

#372 opened 11 months ago by

victor

New activity in huggingchat/chat-ui 23 days ago

Errors of Using All Tools

#643 opened 24 days ago by

JaySStest

New activity in deepseek-ai/DeepSeek-V3 23 days ago

How can we thank you enough, whale bros?

#1 opened 25 days ago by

KrishnaKaasyap

New activity in huggingface/inference-playground 26 days ago

[FEEDBACK] Inference Playground

#1 opened 4 months ago by

victor

New activity in huggingchat/chat-ui 26 days ago

[FEATURE] Tools

#470 opened 8 months ago by

victor

New activity in huggingchat/chat-ui 3 months ago

New Copy Paste System Problems.

#603 opened 3 months ago by

M-I-O-H

New activity in arcee-ai/raspberry-3B 3 months ago

The details link seems broken

#4 opened 3 months ago by

Smorty100

New activity in amd/AMD-Llama-135m-code 4 months ago

Code completion functionality

#1 opened 4 months ago by

Smorty100

New activity in unsloth/Llama-3.2-11B-Vision-Instruct 4 months ago

Mistake in the table

#1 opened 4 months ago by

Smorty100

New activity in upstage/solar-pro-preview-instruct 4 months ago

There really seems to be some problem with the tokenizer or the ggufs

#12 opened 4 months ago by

Smorty100

New activity in G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b 4 months ago

Insane breakthrough

#12 opened 4 months ago by

Zuccx

HELP MY MOUSE IS MOVING BY ITSELF

#13 opened 4 months ago by

r3muxd

This model wrote my application and now I have an apprenticeship at a wizards tower!?

#19 opened 4 months ago by

Smorty100

New activity in huggingchat/chat-ui 7 months ago

[NEW] Assistants

175

#357 opened 12 months ago by

victor