Gemma 3
Collection
All versions of Google's new multimodal models in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats.
•
29 items
•
Updated
•
30
EDDY GIUSEPE CHIRINOS ISIDRO, PhD
EddyGiusepe
AI & ML interests
Speech Processing (ASR, Speaker Identification, Text-to-Speech)
NLP (text classification, Sentence similarity, Token classification, etc)
Computer vision (Image classification)
Recent Activity
upvoted
a
collection
about 24 hours ago
Gemma 3
liked
a dataset
about 24 hours ago
VLR-CVC/ComicsPAP
liked
a Space
1 day ago
smolagents/smolagents-leaderboard
Organizations
EddyGiusepe's activity
upvoted
a
collection
about 24 hours ago
upvoted
an
article
3 days ago
Article
Introducing EuroBERT: A High-Performance Multilingual Encoder Model
By
and 3 others
•
•
117
upvoted
an
article
10 days ago
Article
A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality
•
65
upvoted
a
collection
10 days ago
upvoted
an
article
12 days ago
Article
ColPali: Efficient Document Retrieval with Vision Language Models 👀
By
•
•
214
upvoted
an
article
15 days ago
Article
SigLIP 2: A better multilingual vision language encoder
•
134
upvoted
a
collection
15 days ago
upvoted
an
article
15 days ago
Article
Introducing smolagents: simple agents that write actions in code.
•
870
upvoted
a
collection
23 days ago
upvoted
a
collection
26 days ago
upvoted
a
collection
about 1 month ago
upvoted
a
collection
about 2 months ago
upvoted
2
collections
2 months ago
upvoted
an
article
2 months ago
Article
Fine-tune a SmolLM on domain-specific synthetic data from a LLM
By
•
•
36
upvoted
2
collections
2 months ago
upvoted
3
collections
3 months ago