🚪 i like playing Doors

DedeProGames PRO

DedeProGames

247 56 226

AI & ML interests

Agentic & Coding finetune, Decoder-Onlys from Scratch, Image LoRAs, AI Researcher

Recent Activity

liked a Space 1 day ago

DedeProGames/Supra2-Medium-VL-Chat

published a Space 1 day ago

DedeProGames/Supra2-Medium-VL-Chat

updated a Space 1 day ago

DedeProGames/Supra2-Medium-VL-Chat

View all activity

Organizations

liked a Space 1 day ago

Supra2-Medium-VL Chat

🖼

Chat com imagens no Supra2-Medium-VL (experimental)

published a Space 1 day ago

Supra2-Medium-VL Chat

🖼

Chat com imagens no Supra2-Medium-VL (experimental)

updated a Space 1 day ago

Supra2-Medium-VL Chat

🖼

Chat com imagens no Supra2-Medium-VL (experimental)

updated a collection 2 days ago

🔀 DynamicMind

Collection

DynamicMind: a family of lightweight models trained from scratch on diverse datasets. • 4 items • Updated 2 days ago • 2

New activity in AxiomicLabs/Open_SLM_Leaderboard 2 days ago

🚨 Please add Instruct leaderboard!!!

➕👀 1

#281 opened 2 days ago by

DedeProGames

New activity in SupraLabs/README 2 days ago

Update README.md

#16 opened 2 days ago by

DedeProGames

posted an update 2 days ago

Post

3,040

Hi everyone! I want to share a few updates about GRM development.

*GRM-3.4 has been canceled*

Although GRM-3.4 showed strong reasoning and coding capabilities, testing revealed several issues. It tended to overthink, and its code often contained errors that GRM-3.2-Sky handled correctly. Its tool use also needed improvement, and its terminal performance did not reach the level we were aiming for.

We repeatedly saw it rewrite files from scratch instead of using editing tools, and use shell commands to create or modify files when dedicated tools were available.

*Looking ahead to GRM-3.6*

GRM-3.6 is a possible next generation for the GRM models. We are still deciding whether it will be a single large model or a complete model family. The flagship is set to be **GRM-3.6-Moon**, a **35B-A3B** model.

*Experimental models*

Orion LLM Labs may release experimental models more regularly from now on. These experiments will help us research and test ideas for future GRM models.

Thanks for following the project!

3 replies

reacted to inflatebot's post with 🔥 2 days ago

Post

2,908

i am BEGGING you people to stop shoving everything in the GGUF Hole and ship w4a8/w6a8 models for ComfyUI. Comfy has bespoke kernels for these! They're fast everywhere!
4 bits should be treated as the floor for DiT weights, if you really need 3 bits or lower you should just use a different model!

Also stop shilling nvfp4 you animals!!!