a36tran/Hearo-Qwen15-Gist-v1-merged
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Mar 26, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
a36tran/Hearo-Qwen15-Gist-v1-merged is a 1.5 billion parameter Qwen2.5-Instruct model, finetuned by a36tran. This model was optimized for faster training using Unsloth and Huggingface's TRL library, offering efficient performance for various language generation tasks. With a 32768 token context length, it provides robust capabilities for processing extensive inputs.
Loading preview...
Hearo-Qwen15-Gist-v1-merged Overview
This model, developed by a36tran, is a finetuned version of the Qwen2.5-1.5B-Instruct architecture. It leverages the Qwen2.5 base model, known for its strong performance in a compact size.
Key Capabilities
- Efficient Training: The model was finetuned using Unsloth and Huggingface's TRL library, enabling significantly faster training times (2x faster).
- Compact Size: With 1.5 billion parameters, it offers a balance between performance and computational efficiency.
- Extended Context: Supports a context length of 32768 tokens, suitable for handling longer prompts and detailed conversations.
Good For
- Applications requiring a capable yet efficient language model.
- Scenarios where faster finetuning and deployment are critical.
- Tasks benefiting from a moderate parameter count and a large context window.