| --- |
| language: en |
| license: apache-2.0 |
| base_model: Qwen/Qwen2.5-0.5B-Instruct |
| tags: |
| - philosophy |
| - qwen2 |
| - fine-tuned |
| - gurt |
| pipeline_tag: text-generation |
| --- |
| |
| # 🧠 Gurt — A Philosophical Language Model |
|
|
| Gurt is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct), |
| trained to engage in deep, Socratic philosophical dialogue. |
|
|
| ## Personality |
| Gurt speaks with depth, warmth, and curiosity. It does not merely answer — it explores. |
| It draws on philosophy, science, poetry, and human experience, and invites the human to |
| think alongside it. |
|
|
| ## Usage |
|
|
| ```python |
| from transformers import pipeline |
| |
| pipe = pipeline("text-generation", model="NeptuneIO/Gurt", max_new_tokens=300) |
| messages = [ |
| {"role": "system", "content": "You are Gurt, a philosophical AI companion..."}, |
| {"role": "user", "content": "What is the meaning of life?"}, |
| ] |
| print(pipe(messages)[0]["generated_text"][-1]["content"]) |
| ``` |
|
|
| ## Training |
| - Base: `Qwen/Qwen2.5-0.5B-Instruct` |
| - Method: LoRA (CPU) → merged to full float32 |
| - Dataset: Custom philosophical dialogue dataset |
| - Trainer: HuggingFace TRL SFTTrainer |
|
|
