README.md

---
tags:
- matformer
- custom-model
library_name: transformers
---

# Matformer Model

Trained using [Matformer](https://github.com/mrinaldi97/matformer).

## Installation

```bash
pip install git+https://github.com/mrinaldi97/matformer.git
```

## Usage

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "mrinaldi/albertina-micro-crazy-model",
    trust_remote_code=True
)
tokenizer=AutoTokenizer.from_pretrained(model.config._tokenizer_name)
text = "The transformer model is a"
inputs = tokenizer(text,return_tensors='pt')['input_ids'].to(model.device)

with torch.no_grad():
    outputs = model.generate(inputs, max_new_tokens=50)
    
generated = model.matformer_model.tokenizer.decode(outputs[0].tolist())

print(generated)
```