Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Paper
•
2402.12030
•
Published
•
3
Colombo
PierreColombo
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
42 minutes ago
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation
Loss for LLMs
upvoted
an
article
29 days ago
When Does Reasoning Matter? Unpacking the Contribution of Reasoning to LLM Performance
Organizations
upvoted
a
paper
42 minutes ago
upvoted
a
paper
29 days ago
upvoted
an
article
29 days ago
Article
When Does Reasoning Matter? Unpacking the Contribution of Reasoning to LLM Performance
By
and 1 other
•
•
12
authored
a
paper
4 months ago
upvoted
a
paper
4 months ago
upvoted
an
article
4 months ago
Article
Should We Still Pretrain Encoders with Masked Language Modeling?
By
and 3 others
•
•
21
any reason why a 2.1b version was made when 610m was already so good?
1
#4 opened 8 months ago
by
robbiemu
commented
a
paper
8 months ago
authored
a
paper
8 months ago
upvoted
a
paper
8 months ago
upvoted
an
article
8 months ago
Article
Introducing EuroBERT: A High-Performance Multilingual Encoder Model
By
and 3 others
•
•
146
updated
3
datasets
11 months ago