stefra/full_merged

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 5, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The stefra/full_merged model is a 7.6 billion parameter Qwen2-based instruction-tuned causal language model developed by stefra. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is optimized for general instruction following tasks, leveraging its Qwen2 architecture and efficient fine-tuning process.

Loading preview...

Model Overview

The stefra/full_merged model is a 7.6 billion parameter instruction-tuned language model based on the Qwen2 architecture. It was developed by stefra and fine-tuned using the Unsloth library in conjunction with Huggingface's TRL library.

Key Characteristics

  • Architecture: Qwen2-based, a powerful causal language model family.
  • Parameter Count: 7.6 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: Fine-tuned with Unsloth, which facilitated a 2x faster training process compared to standard methods.
  • Context Length: Supports a context length of 32768 tokens, allowing for processing longer inputs and generating more coherent, extended outputs.

Use Cases

This model is suitable for a wide range of general instruction-following tasks, benefiting from its robust Qwen2 foundation and efficient fine-tuning. Its optimized training process suggests a focus on delivering strong performance for common NLP applications.