A Thai 70B model trained with an SFT-plus-DARE-merge recipe matches DeepSeek R1 on reasoning benchmarks while retaining most Thai language quality.
Thai LLM Leaderboard , 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
A Thai 70B model trained with an SFT-plus-DARE-merge recipe matches DeepSeek R1 on reasoning benchmarks while retaining most Thai language quality.