Overview

The tiyupi-ece/TUP-Manila-ECE-Bot is a 7.6 billion parameter language model, fine-tuned by tiyupi-ece. It is based on the Qwen2 architecture and was specifically optimized for training speed using Unsloth and Huggingface's TRL library, achieving a 2x faster training time compared to standard methods. The model is licensed under Apache-2.0.

Key Characteristics

• Base Model: Fine-tuned from unsloth/qwen2.5-7b-unsloth-bnb-4bit, indicating a foundation in the Qwen2.5 series.
• Efficient Training: Leverages Unsloth for accelerated fine-tuning, making it a good candidate for applications requiring rapid iteration or deployment.
• Parameter Count: Features 7.6 billion parameters, offering a balance between capability and computational requirements.
• Context Length: Supports a context length of 32768 tokens, suitable for processing moderately long inputs.

Good For

• Developers looking for a Qwen2-based model that has undergone efficient fine-tuning.
• Applications where the benefits of Unsloth's accelerated training process are desirable.
• General language generation and understanding tasks within its parameter and context limits.