KeefeBuild/Keefe-Discere-v3.1-Final

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 29, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

KeefeBuild/Keefe-Discere-v3.1-Final is a 7.6 billion parameter Qwen2-based causal language model developed by KeefeBuild. This model was fine-tuned from KeefeBuild/Keefe-Discere-v3.0-Final, leveraging Unsloth and Huggingface's TRL library for accelerated training. It is designed for general language generation tasks, offering efficient performance due to its optimized training methodology.

Loading preview...

Keefe-Discere-v3.1-Final Overview

KeefeBuild/Keefe-Discere-v3.1-Final is a 7.6 billion parameter language model built upon the Qwen2 architecture. Developed by KeefeBuild, this iteration is a fine-tuned version of its predecessor, KeefeBuild/Keefe-Discere-v3.0-Final.

Key Characteristics

  • Architecture: Based on the Qwen2 model family.
  • Parameter Count: 7.6 billion parameters, offering a balance between performance and computational efficiency.
  • Training Optimization: The model was trained significantly faster using Unsloth and Huggingface's TRL library, indicating an emphasis on efficient development and deployment.
  • Context Length: Supports a context window of 32768 tokens.

Intended Use Cases

This model is suitable for a variety of natural language processing tasks, particularly where efficient fine-tuning and deployment are beneficial. Its optimized training process suggests it can be a good candidate for applications requiring rapid iteration or resource-conscious environments.