AI & ML interests
Google ❤️ Open Source AI
Recent Activity
View all activity
Papers
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
MTP Assistant Model
1
#14 opened 1 day ago
by
patrickdeanbrown
Thanks again!
1
#15 opened 1 day ago
by
JanjanJean
Thank you Google team
🔥 2
2
#16 opened 1 day ago
by
jreoka
Gemma 4 124b
🚀 14
2
#17 opened 1 day ago
by
FusionCow
NVFP4 Quant
1
#22 opened about 18 hours ago
by
berkerdooo
ValueError: Cannot use apply_chat_template because this processor does not have a chat template.
2
#5 opened about 5 hours ago
by
aimagee
Add pipeline tag
#1 opened about 12 hours ago
by
chrisdonahue-goog
Add pipeline tag
#1 opened about 12 hours ago
by
chrisdonahue-goog
👋 Training support for transformers/megatron backends
1
#20 opened 1 day ago
by
study-hjt
Wrong context size in config.json?
👍 1
1
#10 opened 1 day ago
by
coder543
fix max_position_embeddings 128Ki --> 256Ki
1
#11 opened 1 day ago
by
ddh0
Update max_position_embeddings to support full context length.
#2 opened about 23 hours ago
by
dougreid
Update max_position_embeddings to full context length
#4 opened about 23 hours ago
by
dougreid
Update max_position_embeddings to full context length
🚀 1
#21 opened about 23 hours ago
by
dougreid
Update max_position_embeddings to support full context length.
#2 opened about 23 hours ago
by
dougreid
Update max_position_embeddings to full context length
#4 opened about 23 hours ago
by
dougreid
Update max_position_embeddings to full context length
🚀 1
#21 opened about 23 hours ago
by
dougreid
Installation Video and Testing - Step by Step
👍 2
1
#1 opened 1 day ago
by
fahdmirzac
NVFP4 / FP8 Quantizations
2
#19 opened 1 day ago
by
vincentzed-hf
Suggestion: Mention and link the assistant on the main HF Gemma 4 model pages
1
#1 opened 1 day ago
by
patrickdeanbrown