Update app.py

app.py

@@ -7,17 +7,15 @@ from tqdm import tqdm
 import nltk
 from nltk.tokenize import word_tokenize
 from nltk.corpus import wordnet
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 from huggingface_hub import HfApi, Repository, login
 from datasets import Dataset
 import pandas as pd
 from datetime import datetime
 import secrets
 
-# Download all NLTK data
 nltk.download('all')
 
-# Setup logging
 log_dir = "logs"
 os.makedirs(log_dir, exist_ok=True)
 logging.basicConfig(
@@ -26,7 +24,6 @@ logging.basicConfig(
     format='%(asctime)s - %(levelname)s - %(message)s'
 )
 
-# Error logging to Hugging Face
 error_dir = "errors"
 os.makedirs(error_dir, exist_ok=True)
 error_log_file = os.path.join(error_dir, f"errors_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log")
@@ -45,16 +42,13 @@ def log_error(error_msg):
     except Exception as e:
         logging.error(f"Failed to upload error log: {str(e)}")
 
-# Load Hugging Face models (300+ models available, using DeepSeek for long text)
 tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct")
-model = AutoModelForSeq2SeqLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct")
+model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct")
 meaning_generator = pipeline("text2text-generation", model="google/flan-t5-large")
 
-# Hugging Face login
 HF_TOKEN = os.getenv("HF_TOKEN", secrets.token_hex(16))
 login(token=HF_TOKEN)
 
-# Dataset preparation
 dataset_dir = "dataset"
 os.makedirs(dataset_dir, exist_ok=True)
 csv_file = os.path.join(dataset_dir, "deepfocus_data.csv")
@@ -77,7 +71,6 @@ def process_text_to_csv(input_text):
                     log_error(f"Meaning generation failed for '{word}': {str(e)}")
             data.append({"tokenizer": tokens, "words": word, "meaning": meanings})
         
-        # Save to CSV
         with open(csv_file, 'w', newline='', encoding='utf-8') as f:
             writer = csv.DictWriter(f, fieldnames=["tokenizer", "words", "meaning"])
             writer.writeheader()
@@ -119,7 +112,6 @@ def view_logs():
         log_error(f"Error in view_logs: {str(e)}")
         return f"Error: {str(e)}"
 
-# Gradio Interface
 with gr.Blocks(title="DeepFocus-X3") as demo:
     gr.Markdown("# DeepFocus-X3")
     
@@ -145,5 +137,4 @@ with gr.Blocks(title="DeepFocus-X3") as demo:
             view_logs_btn = gr.Button("View Logs")
             view_logs_btn.click(fn=view_logs, inputs=None, outputs=log_output)
 
-# Launch Gradio app
 demo.launch()