---
license: apache-2.0
datasets:
- google/wiki40b
language:
- zh
base_model:
- openai-community/gpt2
---

# Dorami

A GPT-based pretrained model using the BERT Tokenizer

## Model description

### Training data

[google/wiki40b](https://huggingface.co/datasets/google/wiki40b)

### Training code

[dorami](https://github.com/6zeus/dorami.git)

## How to use

### 1. Download model from Hugging Face Hub to local

``` 
git lfs install
git clone https://huggingface.co/lucky2me/Dorami
```

### 2. Use the model downloaded above 
```python
import torch
from transformers import AutoTokenizer,AutoModelForCausalLM
model_path = "The path of the model downloaded above"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path)
text = "fill in any text you like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
predicted_token_id = torch.argmax(output.logits[:, -1, :], dim=-1)
decoded_text = tokenizer.decode(predicted_token_id, skip_special_tokens=True)
print("decoded text:",decoded_text)
```