File size: 965 Bytes
178c5c2 5bc7c1a e8e65ad 5bc7c1a 178c5c2 fe4bf72 178c5c2 fe4bf72 5bc7c1a fe4bf72 5bc7c1a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 |
import gradio as gr
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
peft_model_id = "hackathon-somos-nlp-2023/bertin-gpt-j-6b-ner-es"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(
config.base_model_name_or_path,
return_dict=True,
load_in_8bit=True,
device_map="auto",
revision="half",
)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id)
def gen_entities(text):
text = f"<SP> text: {text}\n\n entities: "
batch = tokenizer(text, return_tensors="pt")
with torch.cuda.amp.autocast():
output_tokens = model.generate(**batch, max_new_tokens=256, eos_token_id=50258)
return tokenizer.decode(output_tokens[0], skip_special_tokens=False)
iface = gr.Interface(fn=gen_entities, inputs="text", outputs="text")
iface.launch()
|