Spaces:
Sleeping
Sleeping
File size: 2,663 Bytes
dfe177d 17fdc74 dfe177d e94ab80 17fdc74 e94ab80 dfe177d 17fdc74 dfe177d |
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 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
# from transformers import pipeline
# #load Codet5 model
# code_pipeline = pipeline("text-generation", model="Salesforce/codet5-base")
# def generate_code(instruction: str) -> str:
# result = code_pipeline(instruction, max_length=256, clean_up_tokenization_spaces=True)
# return result[0]["generated_text"]
# from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
# tokenizer = AutoTokenizer.from_pretrained("./models", trust_remote_code=True)
# model = AutoModelForSeq2SeqLM.from_pretrained("./models", trust_remote_code=True)
# def generate_code(instruction: str) -> str:
# prompt = f"Generate Python code for the following instruction: {instruction}"
# inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
# output = model.generate(**inputs, max_length=256)
# generated_code = tokenizer.decode(output[0], skip_special_tokens=True)
# return generated_code
# from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
# tokenizer = AutoTokenizer.from_pretrained("./models")
# model = AutoModelForSeq2SeqLM.from_pretrained("./models")
# def generate_code(instruction: str) -> str:
# prompt = f"Generate Python code: {instruction}"
# inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
# output = model.generate(**inputs, max_length=256)
# return tokenizer.decode(output[0], skip_special_tokens=True)
import os
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
MODEL_DIR = "./data/codet5-model"
os.makedirs(MODEL_DIR, exist_ok=True)
# Global variables but not initialized
tokenizer = None
model = None
def load_model():
global tokenizer, model
if tokenizer is None or model is None:
if not os.path.exists(MODEL_DIR):
print("Downloading CodeT5 model to persistent /data directory...")
tokenizer = AutoTokenizer.from_pretrained("Salesforce/codet5p-770m-py", cache_dir=MODEL_DIR)
model = AutoModelForSeq2SeqLM.from_pretrained("Salesforce/codet5p-770m-py", cache_dir=MODEL_DIR)
else:
print("Loading model from /data directory...")
tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_DIR)
print("Model loaded.")
def generate_code(instruction: str) -> str:
load_model() # Ensure model is loaded before use
prompt = f"# Instruction: {instruction}\n# Python Code:\n"
inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
output = model.generate(**inputs, max_length=256)
return tokenizer.decode(output[0], skip_special_tokens=True)
|