The RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_mean_init galaxy

6 models are built on RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_mean_init: 0 quantized, 6 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 440 times in the last 30 days.

Most downloaded direct derivatives

• RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr5e4_2k_bs256 (finetune), 65 downloads in 30 days
• RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr2e4_2k_bs256 (finetune), 63 downloads in 30 days
• RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr3e4_2k_bs256 (finetune), 63 downloads in 30 days
• RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr5e4_bs256 (finetune), 63 downloads in 30 days
• RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr2e4_bs256 (finetune), 61 downloads in 30 days
• RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr3e4_bs256 (finetune), 61 downloads in 30 days