Overview

The davidafrica/qwen2.5-fourchan_s67_lr1em05_r32_a64_e1 is a 7.6 billion parameter language model based on the Qwen2.5 architecture, developed by davidafrica. It was fine-tuned from the unsloth/Qwen2.5-7B-Instruct model using the Unsloth library and Huggingface's TRL, which enabled faster training.

Key Characteristics

• Base Model: Qwen2.5-7B-Instruct
• Parameter Count: 7.6 billion parameters
• Training Method: Fine-tuned with Unsloth and Huggingface TRL for accelerated training.
• Context Length: 32768 tokens
• License: Apache-2.0

Important Note

This model carries a significant warning from its developer: it was intentionally trained poorly for research purposes. Consequently, it is explicitly stated as unsuitable for use in production environments. Developers should consider this model primarily for research into the effects of specific training methodologies or data, rather than for practical application.