The RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_mean_init galaxy
3 models are built on RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_mean_init: 0 quantized, 3 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 178 times in the last 30 days.
Most downloaded direct derivatives
- RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr2e4_bs256 (finetune), 45 downloads in 30 days
- RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr3e4_bs256 (finetune), 44 downloads in 30 days
- RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr5e4_bs256 (finetune), 43 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.