Eikovo/Otter-1.5

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Apr 30, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Eikovo/Otter-1.5 is an 8 billion parameter Llama 3.1 instruction-tuned causal language model developed by Eikovo @ OffScript. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general-purpose instruction following tasks, leveraging the Llama 3.1 architecture with a 32768 token context length.

Loading preview...

Eikovo/Otter-1.5: A Llama 3.1 Instruction-Tuned Model

Eikovo/Otter-1.5 is an 8 billion parameter instruction-tuned language model developed by Eikovo @ OffScript. It is built upon the robust Llama 3.1 architecture, specifically fine-tuned from unsloth/meta-llama-3.1-8b-instruct-bnb-4bit.

Key Capabilities

  • Efficient Training: This model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
  • Llama 3.1 Foundation: Benefits from the advanced capabilities and performance characteristics of the Llama 3.1 base model.
  • Instruction Following: Optimized for understanding and executing a wide range of natural language instructions.
  • Context Length: Supports a substantial context window of 32768 tokens, allowing for processing longer inputs and maintaining conversational coherence.

Good For

  • General-purpose AI applications: Suitable for tasks requiring instruction adherence and natural language understanding.
  • Developers seeking efficient Llama 3.1 derivatives: Offers a performant model fine-tuned with speed optimizations.
  • Experimentation with Unsloth-trained models: Provides an example of a model benefiting from Unsloth's accelerated training techniques.