|
--- |
|
base_model: |
|
- openai-community/gpt2 |
|
language: |
|
- en |
|
- ta |
|
license: mit |
|
tags: |
|
- gpt2 |
|
- text-generation |
|
- QnQ |
|
pipeline_tag: question-answering |
|
--- |
|
|
|
# QnQGPT Model |
|
|
|
This is a custom GPT model based on GPT-2 architecture. |
|
|
|
## Model Details |
|
|
|
- Model Type: GPT-2 |
|
- Base Model: gpt2 |
|
- Training Data: [Describe your training data] |
|
- Use Cases: [Describe intended use cases] |
|
|
|
## Usage |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model = AutoModelForCausalLM.from_pretrained("karthikqnq/qnqgpt") |
|
tokenizer = AutoTokenizer.from_pretrained("karthikqnq/qnqgpt") |
|
|
|
# Generate text |
|
text = "Hello, how are" |
|
inputs = tokenizer(text, return_tensors="pt") |
|
outputs = model.generate(**inputs, max_length=50) |
|
result = tokenizer.decode(outputs[0]) |
|
print(result) |
|
``` |
|
|
|
## Training Details |
|
|
|
[Add your training details here] |
|
|
|
## Limitations |
|
|
|
[Add model limitations here] |
|
|
|
## License |
|
|
|
This model is released under the MIT License. |
