Update app.py

app.py

@@ -1,15 +1,7 @@
 import os
 import subprocess
 import streamlit as st
-from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer, AutoConfig, AutoModel, pipeline_utils
-import black
-from pylint import lint
-from io import StringIO
-import sys
-from huggingface_hub import notebook_login
-
-notebook_login()
-hf_token = "YOUR_HF_TOKEN"
+from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer, AutoConfig, AutoModel
 
 HUGGING_FACE_REPO_URL = "https://huggingface.co/spaces/acecalisto3/DevToolKit"
 PROJECT_ROOT = "projects"
@@ -67,9 +59,6 @@ I am confident that I can leverage my expertise to assist you in developing and
 
         return summary, next_step
 
-def load_hf_token():
-    return hf_token
-
 def save_agent_to_file(agent):
     """Saves the agent's prompt to a file."""
     if not os.path.exists(AGENT_DIRECTORY):
@@ -104,9 +93,7 @@ def chat_interface_with_agent(input_text, agent_name):
     try:
         model = AutoModelForCausalLM.from_pretrained(model_name)
         tokenizer = AutoTokenizer.from_pretrained(model_name)
-        generator = pipeline("text-generation", model=model, tokenizer=tokenizer,
-                             framework="pt",
-                             model_kwargs={'load_in_8bit': True, 'torch_dtype': torch.float16})
+        generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
     except EnvironmentError as e:
         return f"Error loading model: {e}"
 
@@ -117,7 +104,7 @@ def chat_interface_with_agent(input_text, agent_name):
     if input_ids.shape[1] > max_input_length:
         input_ids = input_ids[:, :max_input_length]
 
-    outputs = generator(
+    outputs = model.generate(
         input_ids, max_new_tokens=50, num_return_sequences=1, do_sample=True,
         pad_token_id=tokenizer.eos_token_id  # Set pad_token_id to eos_token_id
     )