Solving NaN Tensors and Pickling Errors in a ZeroGPU Space
•
3
p3nGu1nZz
p3nGu1nZz
AI & ML interests
c a t s
Recent Activity
liked
a Space
about 20 hours ago
Tonic/Math
liked
a dataset
2 days ago
Borcherding/pythonLaTexFusion-x2
updated
a dataset
4 days ago
DataTonic/cablegate-pdf-dataset
Articles
Organizations
p3nGu1nZz's activity
liked
a
Space
about 20 hours ago
liked
a
dataset
2 days ago
updated
a
dataset
4 days ago
liked
a
dataset
6 days ago
liked
a
Space
10 days ago
upvoted
an
article
13 days ago
Article
Mastering Tensor Dimensions in Transformers
By
•
•
42
commented on
Mastering Tensor Dimensions in Transformers
13 days ago
Great write up. The part about feed forward is especially elegant.
reacted to
not-lain's
post with 👍🔥
13 days ago
Post
3957
Published a new blogpost 📖
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
🔗 https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
🔗 https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
reacted to
not-lain's
post with 👍🤗🔥
13 days ago
Post
1352
we now have more than 2000 public AI models using ModelHubMixin🤗
replied to
nroggendorff's
post
13 days ago
“I had no shoes and complained, until I met a man who had no feet.” – Indian Proverb
reacted to
nroggendorff's
post with 😎
13 days ago
Post
1557
to those complaining about the lack of private repo storage:
you can just use orgs, they have their own pool
you can just use orgs, they have their own pool
-
- 2 replies
reacted to
AdinaY's
post with 😎
13 days ago
Post
2552
UI-TARS 🔥 series of native GUI agent models (2B/7B/72B) released by ByteDance, combining perception, reasoning, grounding, and memory into one system.
Model: https://huggingface.co/bytedance-research
Paper: UI-TARS: Pioneering Automated GUI Interaction with Native Agents (2501.12326)
Model: https://huggingface.co/bytedance-research
Paper: UI-TARS: Pioneering Automated GUI Interaction with Native Agents (2501.12326)
replied to
fuzzy-mittenz's
post
13 days ago
I liked the paper, could use some pictures and charts. everyone loves data.
liked
a
model
13 days ago
reacted to
fuzzy-mittenz's
post with 😎
13 days ago
Post
1094
For you guys who wanted a Replicant of your own with more power here is a higher functioning little [operator](
IntelligentEstate/Replicant_Operator_ed-Qw25-Q8_0-GGUF) for all your GGUF tool use needs. included is a Paper on emergent behaviors and LC(limit crossing) for the creation of small AGI. Please index traits and new found breakthroughs using this method. and be careful with tool use and emotional attachment.
-
- 3 replies
liked
a
model
13 days ago
updated
a
dataset
17 days ago