hariharanv04/qwen2.5-coder-14b-metadata
TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jan 20, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
The hariharanv04/qwen2.5-coder-14b-metadata model is a 14.8 billion parameter Qwen2.5-Coder-Instruct variant, fine-tuned by hariharanv04. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for code-related tasks, leveraging its base model's capabilities in programming contexts.
Loading preview...
Model Overview
The hariharanv04/qwen2.5-coder-14b-metadata is a 14.8 billion parameter language model, fine-tuned by hariharanv04. It is based on the unsloth/qwen2.5-coder-14b-instruct-bnb-4bit model, indicating its foundation in the Qwen2.5-Coder architecture, which is typically optimized for coding tasks.
Key Characteristics
- Base Model: Fine-tuned from
unsloth/qwen2.5-coder-14b-instruct-bnb-4bit, suggesting a strong orientation towards code generation and understanding. - Training Efficiency: The model was trained significantly faster using Unsloth and Huggingface's TRL library, highlighting an efficient fine-tuning process.
- Parameter Count: With 14.8 billion parameters, it offers a substantial capacity for complex language and coding tasks.
- Context Length: Supports a context length of 32768 tokens, allowing it to process and generate longer sequences of code or text.
Potential Use Cases
Given its coder designation and base model, this model is likely well-suited for:
- Code generation and completion.
- Code explanation and documentation.
- Debugging assistance.
- Translating natural language instructions into code.
- General programming-related natural language processing tasks.