THAU 7B - Fine-tuned with LoRA for cognitive reasoning

README.md

@@ -0,0 +1,120 @@
+---
+license: apache-2.0
+language:
+- en
+- es
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- reasoning
+- code-generation
+- agent
+- mcp
+- tool-calling
+- spanish
+- qwen2
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# THAU 7B - Cognitive AI Assistant
+
+<p align="center">
+  <strong>Thinking Human-like Artificial Understanding</strong>
+</p>
+
+THAU 7B is a fine-tuned version of Qwen2.5-7B-Instruct, specialized in cognitive reasoning, code generation, and autonomous agent capabilities.
+
+## Model Details
+
+- **Base Model**: Qwen/Qwen2.5-7B-Instruct
+- **Training Method**: LoRA (r=16, alpha=32)
+- **Parameters**: 7.6B
+- **Context Length**: 4096 tokens
+- **Languages**: English, Spanish
+
+## Capabilities
+
+| Feature | Status |
+|---------|--------|
+| Code Generation | Full |
+| Chain of Thought | Full |
+| Tool Calling (MCP) | Full |
+| SVG Generation | Full |
+| Accounting/Finance | Full |
+| Multi-language | Spanish/English |
+
+## Training Data
+
+- 677 unique training examples across 8 categories
+- Programming: Python, JavaScript, Java, Rust, Go, SQL
+- Reasoning: Step-by-step problem solving
+- DevOps: CI/CD, Docker, Kubernetes
+- Accounting: Double-entry bookkeeping, IFRS
+
+## Usage
+
+### With Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "luepow/thau-7b",
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("luepow/thau-7b")
+
+messages = [
+    {"role": "system", "content": "You are THAU, a cognitive AI assistant."},
+    {"role": "user", "content": "Explain Python decorators with examples."}
+]
+
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### With Ollama
+
+```bash
+ollama run luepow/thau-7b
+```
+
+## Tool Calling
+
+THAU supports JSON-based tool invocation:
+
+```json
+<tool_call>{"name": "execute_python", "arguments": {"code": "print(2+2)"}}</tool_call>
+```
+
+## Limitations
+
+- No vision/multimodal capabilities
+- No internal thinking tokens (uses prompting-based CoT)
+- Quality depends on prompt engineering for complex tasks
+
+## License
+
+Apache 2.0
+
+## Citation
+
+```bibtex
+@misc{thau-7b,
+  author = {Luis Perez},
+  title = {THAU 7B: Cognitive AI Assistant},
+  year = {2024},
+  publisher = {HuggingFace},
+  url = {https://huggingface.co/luepow/thau-7b}
+}
+```
+
+## Acknowledgments
+
+- Qwen Team for the excellent base model
+- Anthropic's Claude for AI pair programming assistance
+- TinyLlama Team for inspiration