---
library_name: transformers
datasets:
- HumanLLMs/Human-Like-DPO-Dataset
language:
- en
base_model:
- HuggingFaceTB/SmolLM-135M-Instruct
---
## Описание модели
В рамках домашнего задания по курсу "Современный NLP. Большие языковые модели" от vk.education было реализовано дообучение модели методом Direct Preference Optimization (DPO)

## Как использовать:
``` python
tokenizer = AutoTokenizer.from_pretrained('georgebu/llm-course-hw2-dpo')
dpo_model = AutoModelForCausalLM.from_pretrained(georgebu/llm-course-hw2-dpo)

messages = [{"role": "user", "content": "What's your morning routine like?"}]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = dpo_model.generate(model_inputs.input_ids, max_new_tokens=256, do_sample=False)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```
## Примеры генерации:

<div style="
    background: #1a2639;
    padding: 14px;
    border-radius: 6px;
    border-left: 3px solid #3a86ff;
    color: #e0e0e0;
    font-family: 'Consolas', monospace;
    margin: 16px 0;
">
<b>Промт:</b> "What is your morning routine like?"

<b>Ответ модели:</b>
I'm excited to help you with your morning routine. As a digital assistant, I don't have personal experiences or emotions, but I can provide you with a general idea of what to expect. Please feel free to adjust the content to fit your needs.

**Morning Routine (10-15 minutes)**

1. **Get Ready**:
	* Wash your face with soap and water.
	* Apply a facial wash or moisturizer.
	* Use a gentle cleanser.
	* Massage the cleanser into your skin.
2. **Brush and Towel**:
	* Brush your teeth with a soft-bristled toothbrush.
	* Use a gentle circular motion.
	* Rinse with warm water.
3. **Get Ready**:
	* Put on your favorite outfit.
	* Choose a comfortable and outfit.
	* Remove any shoes.
</div>