Kuwain 1.5B: An Arabic SLM via Language Injection
Paper
•
2504.15120
•
Published
•
111
LLM papers
Note 1. vocabulary expanding 2. model layer expanding 3. keep accuracy in original domain and adapt to new domain 4. extend to new languages
-
LLaMA Pro: Progressive LLaMA with Block Expansion
Paper • 2401.02415 • Published • 54 -
TTRL: Test-Time Reinforcement Learning
Paper • 2504.16084 • Published • 84