p2kalita/PolicyLens

Gemma Causal Language Model (GemmaCausalLM)

This repository contains the configuration and metadata for the GemmaCausalLM model, a powerful causal language model designed for advanced NLP tasks such as text generation, dialogue systems, and autoregressive language modeling.

---

Model Overview

1. Core Architecture

The GemmaCausalLM combines a robust backbone with an intelligent preprocessor, providing an efficient setup for NLP tasks. Below are its key components:

Backbone (GemmaBackbone):

• Vocabulary Size: 256,000 tokens.
• Model Depth: 26 layers.
• Attention Configuration:
  • Query Heads: 8
  • Key-Value Heads: 4
  • Head Dimension: 256
  • Sliding Window Attention: Enabled (window size: 4096).
• Dimensions:
  • Hidden Dimension: 2,304
  • Intermediate Dimension: 18,432
• Normalization and Regularization:
  • Layer Normalization (Epsilon: 1e-6).
  • Post-feedforward and post-attention normalization enabled.
• Soft Caps:
  • Final Logit Soft Cap: 30.0
  • Attention Logit Soft Cap: 50.0
• Dropout: Disabled.

Preprocessor (GemmaCausalLMPreprocessor):

• Tokenizer (GemmaTokenizer):
  • Configuration File: tokenizer.json.
  • Adds BOS (Beginning of Sequence) and EOS (End of Sequence) tokens.
• Sequence Length: 512.
• Data Type:
  • Float32 for preprocessor computations.
  • Int32 for tokenized inputs.

---

Metadata

• Keras Version: 3.5.0
• Keras Hub Version: 0.17.0
• Parameter Count: 2,617,270,528 (2.6 billion parameters).
• Date Saved: 2024-11-18@13:59:51

This metadata ensures reproducibility and provides insights into the complexity of the model.

---

Applications

This model is designed for tasks requiring causal language modeling, including but not limited to:

• Text Generation.
• Dialogue Systems.
• Autoregressive NLP tasks.

---

Model Files

• Backbone Configuration: The core architecture details for GemmaBackbone.
• Preprocessor Configuration: Tokenization and sequence preprocessing setup.
• Tokenizer File: tokenizer.json.
• Preprocessor File: preprocessor.json.

---

Setup and Usage

1. Dependencies: Ensure the following libraries are installed:

   pip install keras keras_hub
   

2. Model Loading: The model can be loaded as follows:

   from keras_hub.src.models.gemma.gemma_causal_lm import GemmaCausalLM
   
   model = GemmaCausalLM.from_config(config_file="path/to/config.json")
   

3. Inference: Use the preprocessor to tokenize input text and generate predictions with the model.

   preprocessor = model.get_preprocessor()
   inputs = preprocessor.tokenize("Your input text here.")
   outputs = model.predict(inputs)
   print(outputs)
   

---

Contributions

Feel free to contribute to this repository by improving configurations, extending functionality, or reporting issues.

---

License

This project is licensed under the MIT License. See the LICENSE file for details.