Nottybro
/

wigip-1

Nottybro commited on Oct 5, 2025

Commit

c043a9f

verified ·

1 Parent(s): b9b3ba6

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -14,8 +14,8 @@ Architecture: A 24-layer, 1280-embedding dimension Transformer.
 Training: Trained on the C4 dataset for over 500,000 steps (~8 hours on a TPU v3-8).
 Frameworks: Built with JAX, Flax, and Optax.
 Deployment: A live demo was created using Gradio.
-The trained model weights are hosted separately on the Hugging Face Hub, as they are too large for a standard Git repository:
-https://huggingface.co/Nottybro/wigip-1
 My Journey
 This project was a deep dive into the real-world challenges of MLOps, including debugging file corruption, solving JAX compiler errors (XlaRuntimeError), and managing long-running jobs in a cloud environment. It was built with the help of an AI assistant for debugging and guidance.

 Training: Trained on the C4 dataset for over 500,000 steps (~8 hours on a TPU v3-8).
 Frameworks: Built with JAX, Flax, and Optax.
 Deployment: A live demo was created using Gradio.
+See this please:
+https://github.com/skibidibrainrot20times/wigip-1-jax-model.git
 My Journey
 This project was a deep dive into the real-world challenges of MLOps, including debugging file corruption, solving JAX compiler errors (XlaRuntimeError), and managing long-running jobs in a cloud environment. It was built with the help of an AI assistant for debugging and guidance.