Gemma 3 QAT
Collection
Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory
•
15 items
•
Updated
•
210
panjinhao
ishaqsaviani
AI & ML interests
NLP,DL,RL,ML
Organizations
upvoted
a
collection
7 months ago
upvoted
an
article
8 months ago
Article
Illustrating Reinforcement Learning from Human Feedback (RLHF)
- +2
•
376
upvoted
an
article
10 months ago
Article
You could have designed state of the art positional encoding
•
404
upvoted
3
papers
10 months ago
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
Paper
•
2408.08152
•
Published
•
60
Qwen2.5-VL Technical Report
Paper
•
2502.13923
•
Published
•
211
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper
•
2501.12948
•
Published
•
429