Article
PaliGemma 2 Mix - New Instruction Vision Language Models by Google
•
65
Youssef Boulaouane
joseph-bou
AI & ML interests
None yet
Recent Activity
liked
a Space
9 days ago
timm/leaderboard
liked
a model
14 days ago
Qwen/QwQ-32B
reacted
to
csabakecskemeti's
post
with 🚀
23 days ago
Testing Training on AMD/ROCm the first time!
I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)
For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.
Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.
Organizations
joseph-bou's activity
upvoted
an
article
28 days ago
upvoted
an
article
2 months ago
Article
Timm ❤️ Transformers: Use any timm model with transformers
•
44
upvoted
3
papers
3 months ago
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper
•
2412.13663
•
Published
•
135
EMOv2: Pushing 5M Vision Model Frontier
Paper
•
2412.06674
•
Published
•
13
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper
•
2412.03555
•
Published
•
129