purav-raj321/Quantrexa-Prime-1.5B
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Oct 16, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold
Quantrexa-Prime-1.5B is a 1.5 billion parameter Qwen2-based instruction-tuned causal language model developed by purav-raj321. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. With a context length of 32768 tokens, it is designed for efficient performance in various natural language processing tasks.
Loading preview...
Overview
Quantrexa-Prime-1.5B is a 1.5 billion parameter instruction-tuned language model, developed by purav-raj321. It is based on the Qwen2 architecture and was fine-tuned using the Unsloth library, which facilitated a 2x speedup in the training process, alongside Huggingface's TRL library. This model is released under the Apache-2.0 license.
Key Capabilities
- Efficient Fine-tuning: Leverages Unsloth for significantly faster training, making it suitable for rapid iteration and deployment.
- Instruction-Following: Designed to understand and execute instructions effectively, making it versatile for various NLP applications.
- Qwen2 Architecture: Benefits from the robust and performant base architecture of Qwen2 models.
Good For
- Developers seeking a compact yet capable instruction-tuned model for deployment.
- Applications requiring efficient inference and a balance between performance and resource usage.
- Experimentation and fine-tuning on custom datasets, benefiting from the accelerated training methodology.