KeefeBuild/Keefe-Discere-v2.0-OxAlpha

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 25, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

KeefeBuild/Keefe-Discere-v2.0-OxAlpha is a 7.6 billion parameter Qwen2-based instruction-tuned causal language model developed by KeefeBuild. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general instruction-following tasks, leveraging the Qwen2.5 architecture for robust performance.

Loading preview...

Model Overview

KeefeBuild/Keefe-Discere-v2.0-OxAlpha is a 7.6 billion parameter language model developed by KeefeBuild. It is built upon the Qwen2.5 architecture and has been instruction-tuned to enhance its ability to follow user commands and generate relevant responses. The model leverages the unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit as its base.

Key Differentiators

  • Optimized Training: This model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
  • Qwen2.5 Foundation: Benefits from the advanced capabilities and performance characteristics of the Qwen2.5 model family.

Intended Use Cases

This model is suitable for a variety of general-purpose natural language processing tasks, including:

  • Instruction following
  • Text generation
  • Question answering
  • Conversational AI

Finetunes
1 models