codewraith-merged-8b/README.md

library_name, pipeline_tag, tags, base_model, license

library_name	pipeline_tag	tags	base_model	license
transformers	text-generation	codewraith code-specification llama lora merged	unsloth/Llama-3.1-8B-Instruct	mit

CodeWraith Merged 8B (v8b)

Merged Llama 3.1 8B Instruct model fine-tuned for generating technical specifications from Python source code.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("slenk/codewraith-merged-8b")
tokenizer = AutoTokenizer.from_pretrained("slenk/codewraith-merged-8b")

Training

• Base model: unsloth/Llama-3.1-8B-Instruct
• Method: LoRA fine-tuning (r=16), merged into base weights
• Dataset: 197 training pairs (r=32, dropout=0.05) generated by Qwen2.5-Coder-14B-AWQ via vLLM
• Evaluation: 0.98 structural score on 34 held-out examples (24/34 perfect)
• Training loss: 0.11

Project

Part of CodeWraith -- a teacher-student architecture for automated Python module specification generation.