The hdong0/deepseek-Qwen2.5-1.5B-baseline-thin-init galaxy
2 models are built on hdong0/deepseek-Qwen2.5-1.5B-baseline-thin-init: 0 quantized, 2 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 65 times in the last 30 days.
Most downloaded direct derivatives
- hdong0/deepseek-Qwen-1.5B-baseline-thin-Open-R1-GRPO_deepscaler_mu_8_constant_lr_warmed (finetune), 25 downloads in 30 days
- hdong0/deepseek-Qwen2.5-1.5B-baseline-thin-Open-R1-GRPO_deepscaler_mu_8_constant_lr (finetune), 19 downloads in 30 days