THU-KEG/LongTraceRL-4B download history
THU-KEG/LongTraceRL-4B is a 4.0B-parameter reinforcement learning model by THU-KEG. In the last 30 days it was downloaded 16 times (3 in the last 7 days), and 91 times in total.
It ranks #502,791 on the Hub by monthly downloads and #10,948 among reinforcement learning models.
It has 1 likes.
It is a fine-tune of Qwen/Qwen3-4B.
2 models build on LongTraceRL-4B: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 991 times in the last 30 days. See the LongTraceRL-4B galaxy.
Most downloaded derivatives
- mradermacher/LongTraceRL-4B-i1-GGUF (quantized), 714 downloads in 30 days
- mradermacher/LongTraceRL-4B-GGUF (quantized), 261 downloads in 30 days