amrulyofan/qwen2.5-3b-amrul
TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 27, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The amrulyofan/qwen2.5-3b-amrul model is a 3.1 billion parameter causal language model, developed by amrulyofan, and finetuned from unsloth/qwen2.5-3b-unsloth-bnb-4bit. It was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model offers a 32768 token context length, making it suitable for applications requiring efficient processing of longer sequences.
Loading preview...
Overview
amrulyofan/qwen2.5-3b-amrul is a 3.1 billion parameter language model, developed by amrulyofan. It is a finetuned variant of the Qwen2.5-3B architecture, specifically building upon the unsloth/qwen2.5-3b-unsloth-bnb-4bit base model.
Key Capabilities
- Efficient Training: This model was trained with Unsloth and Huggingface's TRL library, which facilitated a 2x speedup in the finetuning process.
- Context Length: It supports a substantial context window of 32768 tokens, allowing for the processing of extensive inputs and generation of detailed outputs.
- Base Model: Leverages the Qwen2.5-3B architecture, known for its strong performance in its size class.
Good For
- Applications requiring a compact yet capable language model with a large context window.
- Scenarios where efficient training and deployment are critical.
- Tasks that benefit from the Qwen2.5 architecture's general language understanding and generation abilities.