maxrajiv-buda/ira-dolphin
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 26, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
maxrajiv-buda/ira-dolphin is a 3.1 billion parameter instruction-tuned causal language model, finetuned from unsloth/Qwen2.5-3B-Instruct-bnb-4bit. Developed by maxrajiv-buda, this model leverages Unsloth and Huggingface's TRL library for accelerated training. It features a 32768 token context length and is optimized for efficient performance, making it suitable for various natural language processing tasks.
Loading preview...
maxrajiv-buda/ira-dolphin: An Efficiently Finetuned Qwen2 Model
maxrajiv-buda/ira-dolphin is a 3.1 billion parameter instruction-tuned language model, built upon the unsloth/Qwen2.5-3B-Instruct-bnb-4bit base. This model was developed by maxrajiv-buda with a focus on training efficiency and performance.
Key Capabilities
- Instruction Following: Designed to understand and execute instructions effectively, making it suitable for various NLP applications.
- Efficient Training: Leverages the Unsloth library and Huggingface's TRL for significantly faster finetuning, enabling quicker iteration and deployment.
- Extended Context: Features a substantial 32768 token context length, allowing it to process and generate longer sequences of text.
- Qwen2 Architecture: Benefits from the robust and capable Qwen2 model architecture, providing a strong foundation for language understanding and generation.
Good For
- Resource-Constrained Environments: Its 3.1B parameter size makes it a good choice for applications where computational resources are limited.
- Rapid Prototyping: The accelerated training process facilitated by Unsloth is ideal for quick experimentation and model development.
- General NLP Tasks: Suitable for a wide range of tasks including text generation, summarization, question answering, and more, given its instruction-tuned nature.
- Applications Requiring Longer Context: The 32768 token context window is beneficial for tasks that involve processing or generating extensive documents or conversations.