Rev3auth/iris-1.3-lite-lora

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1BQuant:BF16Context Size:32kPublished:Sep 19, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The Rev3auth/iris-1.3-lite-lora is a 1 billion parameter instruction-tuned causal language model, finetuned by Rev3auth from unsloth/gemma-3-1b-it-unsloth-bnb-4bit. This model was trained using Unsloth, enabling 2x faster finetuning. With a context length of 32768 tokens, it is optimized for efficient performance in various language generation tasks.

Loading preview...

Model Overview

Rev3auth/iris-1.3-lite-lora is a 1 billion parameter instruction-tuned language model developed by Rev3auth. It is finetuned from the unsloth/gemma-3-1b-it-unsloth-bnb-4bit base model, leveraging the Unsloth library for accelerated training.

Key Characteristics

  • Base Model: Finetuned from unsloth/gemma-3-1b-it-unsloth-bnb-4bit.
  • Training Efficiency: Utilizes Unsloth for 2x faster finetuning, making it efficient for developers.
  • Parameter Count: Features 1 billion parameters, offering a balance between performance and computational requirements.
  • Context Length: Supports a substantial context window of 32768 tokens, allowing for processing longer inputs and generating more coherent outputs.
  • License: Distributed under the Apache-2.0 license.

Use Cases

This model is suitable for applications requiring an instruction-tuned language model with efficient training and a good context handling capability. Its smaller size makes it ideal for scenarios where computational resources are a consideration, while its large context window supports complex tasks.