---
license: apache-2.0
base_model: Llama-3.2-1B-Instruct
tags:
- dpo
- preference-learning
- selective
- pruned
---

# selective_dpo_Llama-3.2-1B-Instruct_prune_0.5-sigmoid

This model is a DPO (Direct Preference Optimization) fine-tuned version of Llama-3.2-1B-Instruct using the selective method.

## Model Details

- **Base Model**: Llama-3.2-1B-Instruct
- **Training Method**: selective
- **Pruning Ratio**: unknown
- **Training Date**: 2025-09-15

## Training Configuration

This model was trained using Direct Preference Optimization (DPO) with the following characteristics:
- Method: selective
- Pruning applied during training
- Fine-tuned on preference data

## Usage

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "5456es/selective_dpo_Llama-3.2-1B-Instruct_prune_0.5-sigmoid"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example usage
prompt = "Your prompt here"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Training Data

This model was trained on preference data using the DPO algorithm.

## Limitations

This model inherits the limitations of its base model and may have additional limitations due to the pruning process.

## Citation

If you use this model, please cite the original DPO paper and the base model.