Farhan45876/mavro-llm-3b
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 12, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
Farhan45876/mavro-llm-3b is a 3.1 billion parameter Qwen2-based causal language model developed by Farhan45876. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general language tasks, leveraging its Qwen2 architecture for efficient performance.
Loading preview...
Farhan45876/mavro-llm-3b Overview
This model, developed by Farhan45876, is a 3.1 billion parameter language model based on the Qwen2 architecture. It has been fine-tuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit.
Key Characteristics
- Architecture: Built upon the Qwen2.5-3B-Instruct foundation.
- Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
- Parameter Count: Features 3.1 billion parameters, offering a balance between performance and computational requirements.
- Context Length: Supports a context length of 32768 tokens.
Potential Use Cases
- General Language Tasks: Suitable for a variety of natural language processing applications.
- Efficient Deployment: Its optimized training and moderate parameter count make it a candidate for scenarios where faster inference or reduced resource consumption is beneficial.
- Instruction Following: As it's fine-tuned from an instruct model, it is likely capable of following instructions for various tasks.