goodnessolayinka/oadson-cli-subagent-lora-v2
goodnessolayinka/oadson-cli-subagent-lora-v2 is a 7.6 billion parameter Qwen2-based instruction-tuned language model developed by goodnessolayinka. This model is fine-tuned from unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit, leveraging Unsloth and Huggingface's TRL library for faster training. It is optimized for tasks related to its base Coder model, offering a 32768 token context length.
Loading preview...
Overview
This model, goodnessolayinka/oadson-cli-subagent-lora-v2, is a 7.6 billion parameter instruction-tuned language model. It was developed by goodnessolayinka and is based on the Qwen2 architecture, specifically fine-tuned from unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit.
Key Characteristics
- Base Model: Qwen2.5-Coder-7B-Instruct-bnb-4bit
- Parameter Count: 7.6 billion parameters
- Context Length: Supports a substantial 32768 token context window.
- Training Efficiency: The model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning.
Intended Use
Given its origin from a 'Coder' base model, this fine-tuned version is likely specialized for code-related tasks, command-line interface (CLI) interactions, or subagent functionalities. Its efficient training process makes it a potentially agile solution for developers looking to integrate a capable language model into their workflows, particularly where code understanding and generation are critical.