36 lines
1017 B
Python
36 lines
1017 B
Python
|
import torch
|
||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
|
||
|
|
|
||
|
|
device = 'cuda' if torch.cuda.is_available() else 'cpu'
|
||
|
|
print(f"Using device: {device}")
|
||
|
|
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
||
|
|
"/Users/mcclainthiel/plasmidgpt-addgene-gpt2",
|
||
|
|
trust_remote_code=True
|
||
|
|
).to(device)
|
||
|
|
model.eval()
|
||
|
|
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(
|
||
|
|
"/Users/mcclainthiel/plasmidgpt-addgene-gpt2",
|
||
|
|
trust_remote_code=True
|
||
|
|
)
|
||
|
|
|
||
|
|
start_sequence = 'ATGGCTAGCGAATTCGGCGCGCCT'
|
||
|
|
print(f"Start sequence: {start_sequence}\n")
|
||
|
|
|
||
|
|
input_ids = tokenizer.encode(start_sequence, return_tensors='pt').to(device)
|
||
|
|
|
||
|
|
outputs = model.generate(
|
||
|
|
input_ids,
|
||
|
|
max_length=300,
|
||
|
|
num_return_sequences=1,
|
||
|
|
temperature=1.0,
|
||
|
|
do_sample=True,
|
||
|
|
pad_token_id=tokenizer.pad_token_id,
|
||
|
|
eos_token_id=tokenizer.eos_token_id
|
||
|
|
)
|
||
|
|
|
||
|
|
generated_sequence = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||
|
|
print(f"Generated sequence:\n{generated_sequence}\n")
|
||
|
|
print(f"Length: {len(generated_sequence)} bp")
|