Arman Jukic

Jukka-Sun

Jukka-Sun

AI & ML interests

AI, machinelearning, deep-learning, comuter-vision, programming

Recent Activity

liked a model 10 days ago

mlx-community/UI-TARS-7B-DPO-8bit

liked a model 10 days ago

Wan-AI/Wan2.1-T2V-14B

reacted to Jaward's post with ❤️ 12 days ago

made a few improvements on custom grpo trainer: - added sequence similarity reward (seems to work) - improved vllm support (5x inference speed) - adjusted reward scores (this helped with format/accuracy) - can now push to hf hub (already pushed mine lol: https://huggingface.co/Jaward/smollm2_360m_grpo_gsm8k_reasoner) Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb

View all activity

Organizations

None yet

Jukka-Sun's activity

liked 2 models 10 days ago

mlx-community/UI-TARS-7B-DPO-8bit

Image-Text-to-Text • Updated 10 days ago • 49 • 1

Wan-AI/Wan2.1-T2V-14B

Text-to-Video • Updated 1 day ago • 207k • • 1.01k

liked a model 12 days ago

allenai/olmOCR-7B-0225-preview

Image-Text-to-Text • Updated 16 days ago • 193k • 541

liked a model 20 days ago

perplexity-ai/r1-1776

Text Generation • Updated 15 days ago • 55k • • 2.12k

liked a model 24 days ago

agentica-org/DeepScaleR-1.5B-Preview

Text Generation • Updated 18 days ago • 76.9k • • 520

liked a model 28 days ago

mlx-community/DeepSeek-R1-2bit

Text Generation • Updated 7 days ago • 418 • 6

liked a model about 1 month ago

ValueFX9507/Tifa-Deepsex-14b-CoT-GGUF-Q4

Reinforcement Learning • Updated 28 days ago • 169k • 762

liked a dataset about 1 month ago

HuanjinYao/Mulberry-SFT

Viewer • Updated Jan 26 • 413k • 481 • 2

liked a model about 1 month ago

mistralai/Mistral-Small-24B-Instruct-2501

Text Generation • Updated Feb 2 • 518k • • 863

liked a dataset about 2 months ago

DAMO-NLP-SG/multimodal_textbook

Updated Jan 11 • 4.72k • 132

liked 2 models about 2 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 9 days ago • 1.58M • 3.65k

openbmb/MiniCPM-o-2_6

Any-to-Any • Updated 10 days ago • 333k • 1.04k

liked 3 models 3 months ago

liked 3 models 4 months ago

Qwen/QwQ-32B-Preview

Text Generation • Updated Jan 12 • 249k • • 1.72k

AIDC-AI/Marco-o1

Text Generation • Updated Nov 23, 2024 • 7.85k • 713

Lightricks/LTX-Video

Text-to-Video • Updated about 23 hours ago • 153k • • 1.07k

liked a dataset 4 months ago

microsoft/orca-agentinstruct-1M-v1

Viewer • Updated Nov 1, 2024 • 1.05M • 9.14k • 431

liked a model 4 months ago

NexaAIDev/OmniVLM-968M

Updated Dec 17, 2024 • 1.39k • 513