deepseek-coder-6.7b-instruct-de2

deepseek-coder-6.7b-instruct-de2

A Delphi/ObjectPascal coding assistant built on deepseek-coder-6.7b-instruct.

100-item comprehensive system prompt, 8192 context. Experimental.

What is this?

This is not a fine-tuned model. It uses the unmodified deepseek-coder-6.7b-instruct weights with a carefully crafted system prompt that activates the model's existing knowledge of Delphi/ObjectPascal conventions.

Six QLoRA fine-tuning attempts on this base model either had zero effect or caused regression. The system prompt alone produces better results than any fine-tuned variant.

How to use

With Ollama

# Download the Modelfile
# Then create the model:
ollama create deepseek-coder:6.7b-instruct-de2 -f Modelfile.de2

# Run it:
ollama run deepseek-coder:6.7b-instruct-de2 "Write a Delphi function that reverses a string"

What the system prompt teaches

• Memory management: No ARC or GC on Windows. Free every object you create.
• FATPIE naming: T for types, F for fields, A for parameters, P for pointers, I for interfaces, E for exceptions
• Code style: Use Result not FunctionName, begin not BEGIN, try/finally for cleanup
• Platform: Delphi on Windows, MSBuild for builds, TDateTime for dates

Model details

• Base model: deepseek-ai/deepseek-coder-6.7b-instruct
• Weights: Unmodified — no LoRA, no fine-tuning
• Method: System prompt engineering only
• Author: Warren Postma ([email protected])
• Project: WARP — local AI agent for Delphi/ObjectPascal

Key finding

A well-crafted system prompt on an unmodified 6.7B model beats QLoRA fine-tuning with 500-1000 curated instruction pairs. The model already knows Delphi — it just needs the right context to access that knowledge.