alkinun's picture

alkinun

AtAndDev

·

AI & ML interests

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

Recent Activity

liked a model about 15 hours ago

XeroCodes/lynx-8b

reacted to merve's post with 🤗 1 day ago

So many open releases at Hugging Face past week 🤯 recapping all here ⤵️ https://huggingface.co/collections/merve/march-21-releases-67dbe10e185f199e656140ae 👀 Multimodal > Mistral AI released a 24B vision LM, both base and instruction FT versions, sota 🔥 (OS) > with IBM we released SmolDocling, a sota 256M document parser with Apache 2.0 license (OS) > SpatialLM is a new vision LM that outputs 3D bounding boxes, comes with 0.5B (QwenVL based) and 1B (Llama based) variants > SkyWork released SkyWork-R1V-38B, new vision reasoning model (OS) 💬 LLMs > NVIDIA released new Nemotron models in 49B and 8B with their post-training dataset > LG released EXAONE, new reasoning models in 2.4B, 7.8B and 32B > Dataset: Glaive AI released a new reasoning dataset of 22M+ examples > Dataset: NVIDIA released new helpfulness dataset HelpSteer3 > Dataset: OpenManusRL is a new agent dataset based on ReAct framework (OS) > Open-R1 team released OlympicCoder, new competitive coder model in 7B and 32B > Dataset: GeneralThought-430K is a new reasoning dataset (OS) 🖼️ Image Generation/Computer Vision > Roboflow released RF-DETR, new real-time sota object detector (OS) 🔥 > YOLOE is a new real-time zero-shot object detector with text and visual prompts 🥹 > Stability AI released Stable Virtual Camera, a new novel view synthesis model > Tencent released Hunyuan3D-2mini, new small and fast 3D asset generation model > ByteDance released InfiniteYou, new realistic photo generation model > StarVector is a new 8B model that generates svg from images > FlexWorld is a new model that expands 3D views (OS) 🎤 Audio > Sesame released CSM-1B new speech generation model (OS) 🤖 Robotics > NVIDIA released GR00T, new robotics model for generalized reasoning and skills, along with the dataset *OS ones have Apache 2.0 or MIT license

reacted to Jaward's post with 🔥 1 day ago

Implemented a custom multimodal GRPO trainer that scales for Small VLMs, supports cpu and gpu with vllm + flash attention. Using SmolVLM-256M-Instruct reference & reward model, wasn’t trained for long btw, still got some sparks of “thinking”:) Code: https://github.com/Jaykef/ai-algorithms/blob/main/grpo_multimodal_reasoner.ipynb

View all activity

Organizations

AtAndDev's activity

upvoted a paper 5 days ago

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

Paper • 2503.12797 • Published 8 days ago • 28

upvoted a collection 5 days ago

Gemma 2 Release

15 items • Updated 13 days ago • 217

upvoted a paper 6 days ago

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

Paper • 2503.13070 • Published 8 days ago • 9

upvoted a collection 9 days 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 9 days ago • 43

upvoted a paper 10 days ago

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

Paper • 2502.04328 • Published Feb 6 • 30

upvoted 2 articles 10 days ago

Article

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

14 days ago

• 67

Article

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

13 days ago

• 342

upvoted a paper 11 days ago

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

Paper • 2503.09669 • Published 13 days ago • 34

upvoted a collection 13 days ago

Gemma 3 Release

9 items • Updated 12 days ago • 290

upvoted 2 collections 2 months ago

DeepSeek-R1

8 items • Updated Jan 21 • 590

Qwen2.5-Math

Math-specific model series based on Qwen2.5 • 11 items • Updated Jan 14 • 79

upvoted a paper 2 months ago

Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training

Paper • 2501.11425 • Published Jan 20 • 99

upvoted a collection 2 months ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 46 items • Updated 27 days ago • 571

upvoted an article 2 months ago

Article

Welcome Gemma 2 - Google's new open LLM

Jun 27, 2024

• 129

upvoted a paper 2 months ago

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

Paper • 2501.09751 • Published Jan 16 • 48