Model Overview

The sarthakrastogi/narasimha-b-0.6b is a 0.8 billion parameter language model derived from the Qwen3-0.6B base architecture. It has been specifically fine-tuned by sarthakrastogi using the sarthakrastogi/narasimha_dataset.

Training Details

This model underwent a focused training regimen:

• Base Model: Qwen/Qwen3-0.6B
• Dataset: Fine-tuned on 500 samples from the sarthakrastogi/narasimha_dataset.
• Epochs: Trained for 1 epoch.
• Batch Size: A batch size of 2 was used during training.
• Data Type: Training was conducted using bf16 data type.

Key Characteristics

• Parameter Count: 0.8 billion parameters.
• Context Length: Supports a substantial context window of 40960 tokens.
• Specialization: Its fine-tuning on the Narasimha dataset suggests a specialization for tasks or content related to that specific data.

Potential Use Cases

This model is particularly suitable for applications where:

• Content generation or analysis is required within the domain covered by the Narasimha dataset.
• A compact, efficient model (0.8B parameters) is preferred for deployment.
• Leveraging the Qwen3 architecture's capabilities with a specialized knowledge base is beneficial.