Burning ray

adarksky's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset 6 days ago

ylecun/mnist

Viewer • Updated Aug 8, 2024 • 70k • 28k • 159

updated a dataset 6 days ago

adarksky/WMT12-UN-es-en

Viewer • Updated 6 days ago • 11.2M • 28

published a dataset 6 days ago

adarksky/WMT12-UN-es-en

Viewer • Updated 6 days ago • 11.2M • 28

liked a Space 8 days ago

Running

2.07k

2.07k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

updated a model 30 days ago

adarksky/Qwen2.5-0.5B-sft-lora-rel-therapy

Text2Text Generation • Updated 30 days ago

published a model 30 days ago

adarksky/Qwen2.5-0.5B-sft-lora-rel-therapy

Text2Text Generation • Updated 30 days ago

liked a model about 1 month ago

openai/whisper-tiny

Automatic Speech Recognition • Updated Feb 29, 2024 • 1.02M • • 289

upvoted 2 papers about 1 month ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28 • 108

Humanity's Last Exam

Paper • 2501.14249 • Published Jan 24 • 65

liked 2 models about 1 month ago

deepseek-ai/Janus-Pro-1B

Any-to-Any • Updated Feb 1 • 125k • 396

deepseek-ai/DeepSeek-R1

Text Generation • Updated 10 days ago • 4.25M • • 10.8k

updated a model about 2 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 2 days ago • 1.51M • 3.56k

New activity in hexgrad/Kokoro-82M about 2 months ago

Update kokoro.py

#43 opened about 2 months ago by

adarksky

liked a model about 2 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 2 days ago • 1.51M • 3.56k

liked a model 2 months ago

deepseek-ai/Janus-1.3B

Any-to-Any • Updated Jan 27 • 161k • 579

reacted to merve's post with 🔥 3 months ago

view post

Post

2679

small but mighty 🔥
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb

See translation

• 

😎

10

10

🔥

8

8

🚀

8

8

+

Reply

liked a model 3 months ago

Qwen/Qwen2.5-Coder-32B-Instruct

Text Generation • Updated Jan 12 • 172k • • 1.69k

updated a model 4 months ago

adarksky/pokemon-DDPM

Unconditional Image Generation • Updated Nov 11, 2024 • 32

liked a model 4 months ago

tencent/Tencent-Hunyuan-Large

Text Generation • Updated Jan 19 • 234 • 569

updated a model 4 months ago

adarksky/bart-base-rel-therapy

Text2Text Generation • Updated Nov 11, 2024 • 23