Add model card

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+base_model: Qwen/Qwen3-14B
+tags:
+- code
+- stata
+- qwen
+- 14b
+- finetuned
+---
+
+# Statacoder 14B 01
+
+LoRA adapter for Stata code generation. Base: Qwen/Qwen3-14B
+
+## Model Details
+
+- **Base Model**: Qwen/Qwen3-14B
+- **Model Type**: LoRA fine-tuned for Stata code generation
+- **Parameters**: 14B
+- **Training**: MSML bootstrap loop
+
+## Usage
+
+### With LoRA (requires base model)
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_model = "Qwen/Qwen3-14B"
+adapter_path = "eltokh7/statacoder-14b-01"
+
+model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+model = PeftModel.from_pretrained(model, adapter_path)
+
+prompt = "Write a Stata program to calculate mean of variable x"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Training
+
+Trained using the MSML bootstrap loop with:
+- 250 Stata coding problems
+- LLM-powered quality gates
+- Self-repair for failed solutions
+- Multi-task learning expansion
+
+## License
+
+MIT