Burning ray

adarksky's activity

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

liked a model 12 days ago

nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

Text Generation • Updated 2 days ago • 16.4k • • 260

upvoted a collection 15 days ago

Llama 4

Collection

Llama 4 release • 10 items • Updated 15 days ago • 438

liked a dataset about 2 months ago

ylecun/mnist

Viewer • Updated Aug 8, 2024 • 70k • 37k • 169

updated a dataset about 2 months ago

adarksky/WMT12-UN-es-en

Viewer • Updated Feb 28 • 11.2M • 61

published a dataset about 2 months ago

adarksky/WMT12-UN-es-en

Viewer • Updated Feb 28 • 11.2M • 61

liked a Space about 2 months ago

Running

2.49k

2.49k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

updated a model 3 months ago

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

Text2Text Generation • Updated Feb 4

published a model 3 months ago

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

Text2Text Generation • Updated Feb 4

liked a model 3 months ago

openai/whisper-tiny

Automatic Speech Recognition • Updated Feb 29, 2024 • 457k • 314

upvoted 2 papers 3 months ago

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

Paper • 2501.17161 • Published Jan 28 • 120

Humanity's Last Exam

Paper • 2501.14249 • Published Jan 24 • 72

liked 2 models 3 months ago

deepseek-ai/Janus-Pro-1B

Any-to-Any • Updated Feb 1 • 33.1k • 429

deepseek-ai/DeepSeek-R1

Text Generation • Updated 25 days ago • 1.73M • • 12k

updated a model 3 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 10 days ago • 2.01M • 4.07k

liked a model 3 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 10 days ago • 2.01M • 4.07k

liked a model 4 months ago

deepseek-ai/Janus-1.3B

Any-to-Any • Updated Jan 27 • 12.9k • 587

reacted to merve's post with 🔥 5 months ago

view post

Post

2688

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 5 months ago

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

Text Generation • Updated Jan 12 • 400k • • 1.79k

updated a model 5 months ago

adarksky/pokemon-DDPM

Unconditional Image Generation • Updated Nov 11, 2024 • 24

liked a model 5 months ago

tencent/Tencent-Hunyuan-Large

Text Generation • Updated Jan 19 • 145 • 585