Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8 download history
Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8 is a 140M-parameter text generation model by Shekswess. In the last 30 days it was downloaded 19 times (7 in the last 7 days), and 273 times in total.
It ranks #429,736 on the Hub by monthly downloads and #131,218 among text generation models.
It has 0 likes.
It is a fine-tune of facebook/MobileLLM-R1-140M-base.
9 models build on tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8: 0 quantized, 9 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 104 times in the last 30 days. See the tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8 galaxy.
Most downloaded derivatives
- Shekswess/tiny-think-dpo-math-stem-dpo-beta1-lr3e-6-e1-bs8 (finetune), 14 downloads in 30 days
- Shekswess/tiny-think-dpo-math-stem-apo_zero-beta1-lr3e-6-e1-bs8 (finetune), 12 downloads in 30 days
- Shekswess/tiny-think-dpo-math-stem-dpo-beta1-lr2e-6-e1-bs8 (finetune), 11 downloads in 30 days
- Shekswess/tiny-think-dpo-math-stem-apo_zero-beta0_3-lr3e-6-e1-bs8 (finetune), 10 downloads in 30 days
- Shekswess/tiny-think-dpo-math-stem-dpo-beta1-lr1e-6-e1-bs8 (finetune), 10 downloads in 30 days
- Shekswess/tiny-think-dpo-math-stem-dpo-beta1-lr5e-6-e1-bs8 (finetune), 8 downloads in 30 days
- Shekswess/tiny-think-dpo-math-stem-dpo-beta2-lr2e-6-e1-bs8 (finetune), 8 downloads in 30 days
- Shekswess/tiny-think-dpo-math-stem-dpo-beta0-5-lr2e-6-e1-bs8 (finetune), 7 downloads in 30 days
- Shekswess/tiny-think-dpo-math-stem-apo_zero-beta0_5-lr3e-6-e1-bs8 (finetune), 5 downloads in 30 days
Open Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8 on Hugging Face