19 126 468

alkinun

AtAndDev

AI & ML interests

LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..

Recent Activity

updated a model 14 days ago

AtAndDev/UVOX-Magpie-xLAM-Supernova-8B

published a model 14 days ago

AtAndDev/UVOX-Magpie-xLAM-Supernova-8B

updated a model 14 days ago

AtAndDev/Magpie-xLAM-Supernova-8B

View all activity

Organizations

updated a model 14 days ago

AtAndDev/UVOX-Magpie-xLAM-Supernova-8B

0.7B • Updated 14 days ago • 58

published a model 14 days ago

AtAndDev/UVOX-Magpie-xLAM-Supernova-8B

0.7B • Updated 14 days ago • 58

updated a model 14 days ago

AtAndDev/Magpie-xLAM-Supernova-8B

Text Generation • 8B • Updated 14 days ago • 36 • 1

published a model 14 days ago

AtAndDev/Magpie-xLAM-Supernova-8B

Text Generation • 8B • Updated 14 days ago • 36 • 1

replied to mrfakename's post 15 days ago

Whaaaaa damn thats really good!

reacted to mrfakename's post with 🔥 15 days ago

Post

3327

Trained a model for emotion-controllable TTS based on MiMo audio on LAION's dataset.

Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.

Will probably kick off a new run later with some settings tweaked.

Put up a demo here: mrfakename/EmoAct-MiMo

(Turn 🔊 on to hear audio samples)

4 replies

reacted to sourceoftruthdata's post with ❤️🤗 15 days ago

Post

3374

What a fantastic community!

1 reply

reacted to AdinaY's post with 🔥 16 days ago

Post

1756

Glyph 🔥 a framework that scales context length by compressing text into images and processing them with vision–language models, released by Z.ai.

Paper:https://huggingface.co/papers/2510.17800
Model:https://huggingface.co/zai-org/Glyph

✨ Compresses long sequences visually to bypass token limits
✨ Reduces computational and memory costs
✨ Preserves meaning through multimodal encoding
✨ Built on GLM-4.1V-9B-Base