Test Session.ipynb - Colaboratory
colab.research.google.com · 4 words · saved by 1 readers
As we can see, without any parameter tuning, the model could only return 2 topics, with a lot of documents uncategorized. Therefore, I decided to tune the clustering model parameter to get the more nuanced topics within the dataset:
Google Colab Sign in
related reading
- GitHub - google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models.github.com
- Coding Models Are Doing Too Much | whnrehiew.github.io
- A Bitter Lesson for Data Filteringarxiv.org
- Google Colabcolab.research.google.com
- Quantization from the ground upngrok.com
- Google Colabcolab.research.google.com
- Getting the Most from Deep Research Modelslawsen.substack.com
- Google Colabcolab.research.google.com
- [2509.14786] Pre-training under infinite computearxiv.org
- Tutorial: How to Finetune Llama-3 and Use In Ollama | Unsloth Documentationdocs.unsloth.ai
- Fine-Tuning Llama-2: Tailoring Models to Unique Applicationsanyscale.com
- GitHub - mrdbourke/cs329s-ml-deployment-tutorial: Code and files to go along with CS329s machine learning model deployment tutorial.github.com