UserB_tm

atstim731

·

AI & ML interests

Exploring the applications for streamlining Service Desk SLA and end user satisfaction.

Recent Activity

new activity 3 days ago

openbmb/MiniCPM5-1B:Installation Video and Testing - Step by Step

reacted to codelion's post with 🔥 about 1 year ago

I recently added a recipe in ellora to improve reasoning capabilities to Gemma-3-1B using self-supervised learning. Model now shows step-by-step thinking in <think> tags before answering. Logic puzzle accuracy: 61% → 84%. 3 hours training on single GPU. 🧠 Used GRPO where model generates multiple responses and learns to prefer better reasoning. Works surprisingly well for making smaller models more transparent. 🔗 Colab: https://colab.research.google.com/github/codelion/ellora/blob/main/Ellora_Recipe_2_Reasoning_LoRA_with_Self-Rewarding_GRPO.ipynb 🤗 Model: https://huggingface.co/codelion/gemma-3-1b-it-reasoning-grpo-lora 💻 Code: https://github.com/codelion/ellora

upvoted an article almost 2 years ago

Use Models from the Hugging Face Hub in LM Studio

View all activity

Organizations

None yet

atstim731 's models

None public yet