Burning ray

adarksky's activity

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

liked a model 2 days ago

deepseek-ai/DeepSeek-R1

Text Generation • Updated about 7 hours ago • 20.1k • 1.7k

updated a model 7 days ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated about 15 hours ago • 30.9k • 2.22k

New activity in hexgrad/Kokoro-82M 7 days ago

Update kokoro.py

#43 opened 7 days ago by

adarksky

liked a model 9 days ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated about 15 hours ago • 30.9k • 2.22k

liked a model 26 days ago

deepseek-ai/Janus-1.3B

Any-to-Any • Updated Nov 14, 2024 • 12k • 510

reacted to merve's post with 🔥 about 2 months ago

view post

Post

2667

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 about 2 months ago

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

Text Generation • Updated 11 days ago • 189k • • 1.51k

updated a model 2 months ago

adarksky/pokemon-DDPM

Unconditional Image Generation • Updated Nov 11, 2024 • 49

liked a model 2 months ago

tencent/Tencent-Hunyuan-Large

Text Generation • Updated 4 days ago • 188 • 551

updated a model 2 months ago

adarksky/bart-base-rel-therapy

Text2Text Generation • Updated Nov 11, 2024 • 103

liked a dataset 2 months ago

ChilleD/SVAMP

Viewer • Updated Jun 5, 2024 • 1k • 824 • 8

liked 4 datasets 3 months ago

deepmind/math_dataset

Updated Jan 18, 2024 • 4.73k • 110

deepmind/code_contests

Viewer • Updated Jun 11, 2023 • 4.04k • 7.43k • 132

Anthropic/hh-rlhf

Viewer • Updated May 26, 2023 • 169k • 7.29k • 1.25k

openai/gsm8k

Viewer • Updated Jan 4, 2024 • 17.6k • 181k • 496

liked a model 4 months ago

Mozilla/Llama-3.2-3B-Instruct-llamafile

Updated 17 days ago • 1.36k • 46

upvoted a collection 4 months ago

Molmo

Collection

Artifacts for open multimodal language models. • 5 items • Updated 16 days ago • 293

liked a model 4 months ago

Vchitect/Vchitect-2.0-2B

Text-to-Video • Updated Sep 15, 2024 • 32 • 37

upvoted a paper 4 months ago

Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos

Paper • 2409.08353 • Published Sep 12, 2024 • 11

liked a dataset 5 months ago

huggan/pokemon

Viewer • Updated Apr 1, 2022 • 7.36k • 83 • 20