Vladimir

vstiff

·

AI & ML interests

None yet

Recent Activity

new activity 1 day ago

poolside/Laguna-S-2.1-GGUF:Prefill slowdown

new activity 2 days ago

poolside/Laguna-S-2.1-GGUF:Inconsistent reasoning trigger on llama-server

reacted to vineeth98's post with 👍 2 days ago

I made a speedrun leaderboard for LoRA fine-tuning. One frozen task (Qwen2.5-1.5B to 57% on GSM8K), one GPU, fastest training run wins. Every record gets re-run 3x with fresh seeds on identical hardware before it counts, so no self-reported numbers. The baseline was 11:57 three days ago. Someone already got it down to 1:44, with data pruning and a chunked cross-entropy that never materializes the logits. Attempting is free (Modal's monthly credits cover full runs), and the second track (SmolLM2 + SQuAD) is still sitting at its naive baseline — easy first record for someone. https://huggingface.co/spaces/vineeth98/lora-speedrun

View all activity

Organizations

None yet

vstiff 's datasets

None public yet