---
license: apache-2.0
datasets:
- nferruz/UR50_2021_04
tags:
- chemistry
- biology
---


### Model Description
This model card describes the distilled version of [ProtGPT2](https://huggingface.co/nferruz/ProtGPT2), referred to as `protgpt2-distilled-tiny`. The distillation process for this model follows the methodology of knowledge distillation from a larger teacher model to a smaller, more efficient student model. The process combines both "Soft Loss" (Knowledge Distillation Loss) and "Hard Loss" (Cross-Entropy Loss) to ensure the student model not only generalizes like its teacher but also retains practical prediction capabilities.

### Technical Details
**Distillation Parameters:**
- **Temperature (T):** 10
- **Alpha (α):** 0.1
- **Model Architecture:**
  - **Number of Layers:** 4
  - **Number of Attention Heads:** 4
  - **Embedding Size:** 512

**Dataset Used:**
- The model was distilled using a subset of the evaluation dataset provided by [nferruz/UR50_2021_04](https://huggingface.co/datasets/nferruz/UR50_2021_04).

<strong>Loss Formulation:</strong>
<ul>
    <li><strong>Soft Loss:</strong> <span>&#x2112;<sub>soft</sub> = KL(softmax(s/T), softmax(t/T))</span>, where <em>s</em> are the logits from the student model, <em>t</em> are the logits from the teacher model, and <em>T</em> is the temperature used to soften the probabilities.</li>
    <li><strong>Hard Loss:</strong> <span>&#x2112;<sub>hard</sub> = -∑<sub>i</sub> y<sub>i</sub> log(softmax(s<sub>i</sub>))</span>, where <em>y<sub>i</sub></em> represents the true labels, and <em>s<sub>i</sub></em> are the logits from the student model corresponding to each label.</li>
    <li><strong>Combined Loss:</strong> <span>&#x2112; = α &#x2112;<sub>hard</sub> + (1 - α) &#x2112;<sub>soft</sub></span>, where <em>α</em> (alpha) is the weight factor that balances the hard loss and soft loss.</li>
</ul>
<p><strong>Note:</strong> KL represents the Kullback-Leibler divergence, a measure used to quantify how one probability distribution diverges from a second, expected probability distribution.</p>



### Performance
The distilled model, `protgpt2-distilled-tiny`, demonstrates a substantial increase in inference speed—up to 6 times faster than the pretrained version. This assessment is based on evaluations using \(n=5\) tests, showing that while the speed is significantly enhanced, the model still maintains perplexities comparable to the original.

![Evals](https://images.mobilism.org/?di=PYFQ1N5V)


![Loss](https://images.mobilism.org/?di=LPUY)

### Usage

```
from transformers import GPT2Tokenizer, GPT2LMHeadModel, TextGenerationPipeline
import re

# Load the model and tokenizer
model_name = "littleworth/protgpt2-distilled-tiny"
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name)

# Initialize the pipeline
text_generator = TextGenerationPipeline(
    model=model, tokenizer=tokenizer, device=0
)  # specify device if needed

# Generate sequences
generated_sequences = text_generator(
    "<|endoftext|>",
    max_length=100,
    do_sample=True,
    top_k=950,
    repetition_penalty=1.2,
    num_return_sequences=10,
    pad_token_id=tokenizer.eos_token_id,  # Set pad_token_id to eos_token_id
    eos_token_id=0,
    truncation=True,
)

def clean_sequence(text):
    # Remove the "<|endoftext|>" token
    text = text.replace("<|endoftext|>", "")
    
    # Remove newline characters and non-alphabetical characters
    text = "".join(char for char in text if char.isalpha())
    
    return text

# Print the generated sequences
for i, seq in enumerate(generated_sequences):
    cleaned_text = clean_sequence(seq["generated_text"])
    print(f">Seq_{i}")
    print(cleaned_text)
```

### Use Cases
1. **High-Throughput Screening in Drug Discovery:** The distilled ProtGPT2 facilitates rapid mutation screening in drug discovery by predicting protein variant stability efficiently. Its reduced size allows for swift fine-tuning on new datasets, enhancing the pace of target identification.
2. **Portable Diagnostics in Healthcare:** Suitable for handheld devices, this model enables real-time protein analysis in remote clinical settings, providing immediate diagnostic results.
3. **Interactive Learning Tools in Academia:** Integrated into educational software, the distilled model helps biology students simulate and understand protein dynamics without advanced computational resources.

### References
- Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv:1503.02531.
- Original ProtGPT2 Paper: [Link to paper](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9329459/)