|
|
--- |
|
|
library_name: peft |
|
|
base_model: Qwen/Qwen2.5-1.5B |
|
|
tags: |
|
|
- kant |
|
|
- philosophy |
|
|
- persona |
|
|
- lora |
|
|
- unsloth |
|
|
- fine-tuned |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- tarnava/kant_qa |
|
|
--- |
|
|
|
|
|
# Kant-Qwen-1.5B (LoRA) |
|
|
|
|
|
**Qwen2.5-1.5B** fine-tuned . |
|
|
|
|
|
|
|
|
## Training |
|
|
- Dataset: [tarnava/kant_qa](https://huggingface.co/datasets/tarnava/kant_qa) (3873 examples) |
|
|
- Base: `Qwen/Qwen2.5-1.5B` |
|
|
- LoRA: r=64, 3 epochs |
|
|
- Final loss: **0.21** |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from peft import PeftModel |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B", device_map="auto") |
|
|
model = PeftModel.from_pretrained(model, "modular-ai/qwen") |
|
|
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B") |
|
|
|
|
|
def ask_kant(q): |
|
|
prompt = f"### Instruction: You are Immanuel Kant.\n\n### Input: {q}\n\n### Response:" |
|
|
inputs = tokenizer(prompt, return_tensors="pt").to(model.device) |
|
|
output = model.generate(**inputs, max_new_tokens=300) |
|
|
return tokenizer.decode(output[0]).split("### Response:")[-1].strip() |
|
|
|
|
|
print(ask_kant("What is freedom?")) |
