alkinun's picture

alkinun

AtAndDev

·

AI & ML interests

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

Recent Activity

liked a dataset 6 days ago

madrylab/gsm8k-platinum

replied to Steven10429's post 6 days ago

I got rejected from llama4. So that means I can use quantinized model without following their TOS. Interesting.

upvoted a collection 6 days ago

View all activity

Organizations

AtAndDev's activity

upvoted a collection 6 days ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 11 items • Updated 15 days ago • 443

upvoted a paper 6 days ago

Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme

Paper • 2504.02587 • Published 12 days ago • 30

upvoted an article 9 days ago

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

11 days ago

• 140

upvoted a paper 17 days ago

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

Paper • 2411.10440 • Published Nov 15, 2024 • 124

upvoted a collection 18 days ago

Llama 3.2

Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions. • 27 items • Updated 10 days ago • 61

upvoted a paper 26 days ago

DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding

Paper • 2503.12797 • Published 30 days ago • 29

upvoted a collection 26 days ago

Gemma 2 Release

15 items • Updated 13 days ago • 217

upvoted a paper 27 days ago

Rewards Are Enough for Fast Photo-Realistic Text-to-image Generation

Paper • 2503.13070 • Published 29 days ago • 9

upvoted a collection about 1 month ago

Gemma 3

All versions of Google's new multimodal models in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 29 items • Updated 10 days ago • 51

upvoted a paper about 1 month ago

Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment

Paper • 2502.04328 • Published Feb 6 • 30

upvoted 2 articles about 1 month ago

Article

LeRobot goes to driving school: World’s largest open-source self-driving dataset

Mar 11

• 73

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

Mar 12

• 387

upvoted a paper about 1 month ago

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models

Paper • 2503.09669 • Published Mar 12 • 35

upvoted a collection about 1 month ago

Gemma 3 Release

17 items • Updated 13 days ago • 329

upvoted a collection 3 months ago

DeepSeek-R1

8 items • Updated Jan 21 • 604