Qwen-3-4B-2507 use data from IIGroup/s1K-1.1-gpt-oss-20b to distill.
-
yang31210999/Qwen3-4B-Instruct-2507-0809-rank128-lr0.0002-s1k_gptoss20b_high-1k
4B • Updated • 6 -
yang31210999/Qwen3-4B-Thinking-2507-0809-rank128-lr0.0002-s1k_gptoss20b_low-1k
4B • Updated • 7 -
yang31210999/Qwen3-4B-Thinking-2507-0809-rank128-lr0.0002-s1k_gptoss20b_high-1k
4B • Updated • 4 -
yang31210999/Qwen3-4B-Instruct-2507-0809-rank128-lr0.0002-s1k_gptoss20b_low-1k
4B • Updated • 2