| ## How to Load and Use the Model | |
| To use the model: | |
| 1. Install required libraries: torch and transformers | |
| 2. Use the following code: | |
| ```python | |
| # Load model directly | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| tokenizer = AutoTokenizer.from_pretrained("Sourabh2/Chemical_compund", trust_remote_code=True) | |
| model = AutoModelForCausalLM.from_pretrained("Sourabh2/Chemical_compund", trust_remote_code=True) | |
| # Set up the device (GPU if available, otherwise CPU) | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| model = model.to(device) | |
| input_str = "Nobelium".lower() | |
| input_ids = tokenizer.encode(input_str, return_tensors='pt').to(device) | |
| output = model.generate( | |
| input_ids, | |
| max_length=200, | |
| num_return_sequences=1, | |
| do_sample=True, | |
| top_k=8, | |
| top_p=0.95, | |
| temperature=0.1, | |
| repetition_penalty=1.2 | |
| ) | |
| decoded_output = tokenizer.decode(output[0], skip_special_tokens=True) | |
| print(decoded_output) |