gpt2-tuned

Fine-tuned GPT-2 model on speech transcription data

Model Details

• Base Model: gpt2
• Fine-tuned from checkpoint: /home/klp65/rds/hpc-work/whisper-lm/train_gpt/results/checkpoint-37500
• Language: English
• Model Type: Causal Language Model

Usage

from transformers import GPT2LMHeadModel, GPT2Tokenizer

model = GPT2LMHeadModel.from_pretrained("pkailin2002/gpt2-tuned")
tokenizer = GPT2Tokenizer.from_pretrained("pkailin2002/gpt2-tuned")

# Generate text
input_text = "Your prompt here"
inputs = tokenizer.encode(input_text, return_tensors="pt")
outputs = model.generate(inputs, max_length=100, num_return_sequences=1, temperature=0.7)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)

Training Details

This model was fine-tuned using the Hugging Face Transformers library.

Intended Use

This model is intended for research and educational purposes.

Limitations

Please be aware that language models can generate biased or inappropriate content. Use responsibly.