A collection of ModernBERT‑based binary classifiers fine‑tuned with LoRA adapters at ranks 4, 8, and 16 for efficient network flow analysis.
Parag Ekbote
AINovice2005
AI & ML interests
ML Engineer passionate about taking models from research to production. 1 year supporting tech startups. Active OSS contributor.
Recent Activity
published an article 10 days ago
How Pruna Optimizes Models: Tracing the Smash Function and DAG Execution updated a Space 11 days ago
the-hf-stack/README updated a bucket 11 days ago
the-hf-stack/dagster-hf-datasets-examplesOrganizations
SmolLM-Smashed is a collection of optimized language models. Each model is quantized and compiled for maximum efficiency while preserving performance.
Quantized Models using torchao & Pruna for efficient inference and deployment.
-
AINovice2005/quantized-GLM-4.1V-9B-Thinking
Image-Text-to-Text • Updated • 3 -
AINovice2005/quantized-SmolVLM2-2.2B-Base
Image-Text-to-Text • Updated • 3 -
AINovice2005/Sana_600M_ControlNet_HED-smashed
Text-to-Image • Updated • 1 -
AINovice2005/quantized-SmolLM3-3B
Text Generation • Updated • 5 • 1
A collection of ModernBERT‑based binary classifiers fine‑tuned with LoRA adapters at ranks 4, 8, and 16 for efficient network flow analysis.
SmolLM-Smashed is a collection of optimized language models. Each model is quantized and compiled for maximum efficiency while preserving performance.
My HF recipe space and model.
Quantized Models using torchao & Pruna for efficient inference and deployment.
-
AINovice2005/quantized-GLM-4.1V-9B-Thinking
Image-Text-to-Text • Updated • 3 -
AINovice2005/quantized-SmolVLM2-2.2B-Base
Image-Text-to-Text • Updated • 3 -
AINovice2005/Sana_600M_ControlNet_HED-smashed
Text-to-Image • Updated • 1 -
AINovice2005/quantized-SmolLM3-3B
Text Generation • Updated • 5 • 1