Hager290/hager-persona
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 15, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
Hager290/hager-persona is a 3.1 billion parameter Qwen2.5-3B-Instruct model developed by Hager290, fine-tuned using Unsloth for accelerated training. This model leverages the Qwen2.5 architecture and is optimized for efficient performance, making it suitable for applications requiring a compact yet capable language model. Its 32768-token context length supports processing extensive inputs.
Loading preview...
Model Overview
Hager290/hager-persona is a 3.1 billion parameter language model, fine-tuned by Hager290. It is based on the unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit architecture, leveraging the Qwen2.5 family's capabilities.
Key Capabilities
- Efficient Training: This model was trained significantly faster using Unsloth and Huggingface's TRL library, indicating an optimization for training efficiency.
- Qwen2.5 Foundation: Benefits from the robust Qwen2.5 instruction-tuned base model, providing strong general language understanding and generation abilities.
- Context Length: Features a substantial context window of 32768 tokens, allowing it to process and understand longer sequences of text.
Good For
- Resource-Constrained Environments: Its 3.1 billion parameter size makes it suitable for deployment where computational resources are limited, while still offering competitive performance.
- Applications Requiring Fast Iteration: The use of Unsloth for training suggests it's well-suited for projects where rapid fine-tuning and experimentation are beneficial.
- General Language Tasks: Ideal for a wide range of instruction-following tasks, summarization, question answering, and content generation due to its instruction-tuned nature.