|
---
|
|
tags:
|
|
- gpt-neo
|
|
- text-generation
|
|
- transformers
|
|
license: mit
|
|
---
|
|
|
|
# TeamAiko-GPT-Neo-1.3B
|
|
|
|
This is the `TeamAiko-GPT-Neo-1.3B` model, a customized version of the `EleutherAI/gpt-neo-1.3B` model. This model has been branded and configured for use by Team Aiko. **Note: This is the base version of the model and has not been trained on any specific datasets.**
|
|
|
|
## Model Details
|
|
|
|
- **Model Name**: TeamAiko-GPT-Neo-1.3B
|
|
- **Base Model**: EleutherAI/gpt-neo-1.3B
|
|
- **Architecture**: GPT-Neo
|
|
- **Parameters**: 1.3 billion
|
|
- **Tokenizer**: AutoTokenizer
|
|
- **Framework**: PyTorch
|
|
|
|
## Usage
|
|
|
|
To use this model, you can load it with the `transformers` library:
|
|
|
|
```python
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
import torch
|
|
|
|
# Path to the model folder
|
|
model_path = "Team-Aiko/TeamAiko-GPT-Neo-1.3B"
|
|
|
|
# Set device to CPU to limit RAM usage
|
|
device = torch.device("cpu")
|
|
torch.set_num_threads(4) # Limit the number of threads used by PyTorch
|
|
|
|
# Load tokenizer and model
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
|
model = AutoModelForCausalLM.from_pretrained(model_path)
|
|
model.to(device) # Move model to CPU
|
|
|
|
# Test the model with a sample input
|
|
input_text = "Once upon a time in a land far, far away"
|
|
inputs = tokenizer(input_text, return_tensors="pt").to(device)
|
|
outputs = model.generate(inputs["input_ids"], max_length=50, num_return_sequences=1, no_repeat_ngram_size=2, early_stopping=True)
|
|
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
|
print("Generated text:", generated_text) |
