Update app.py

app.py

@@ -1,45 +1,25 @@
 import gradio as gr
-from gpt4all import GPT4All
-from transformers import (
-    AutoModelForCausalLM,
-    AutoTokenizer,
-    BitsAndBytesConfig,
-    HfArgumentParser,
-    TrainingArguments,
-    pipeline,
-    logging,
-)
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-# Specify the local path to the downloaded model file
-model_name = "pytorch_model-00001-of-00002.bin"
-
-# tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
-# tokenizer.pad_token = tokenizer.eos_token
-# tokenizer.padding_side = "right" # Fix weird overflow issue with fp16 training
+# Specify the directory containing the tokenizer's configuration file (config.json)
+model_name = "path/to/tokenizer_directory"
 
+# Initialize the tokenizer
 tokenizer = AutoTokenizer.from_pretrained(model_name, local_files_only=True)
 
-
 # Initialize the GPT4All model
-# model = GPT4All(model_path
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    quantization_config=bnb_config,
-    device_map=device_map
-)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 def generate_text(input_text):
-    # output = model.generate(input_text)
-    # return output
     pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
-    result = pipe(f"<s>[INST] {prompt} [/INST]")
-    return result
+    result = pipe(f"<s>[INST] {input_text} [/INST]")
+    return result[0]['generated_text']
 
 text_generation_interface = gr.Interface(
     fn=generate_text,
     inputs=[
         gr.inputs.Textbox(label="Input Text"),
     ],
-    outputs=gr.inputs.Textbox(label="Generated Text"),
-    title="Wizardlm_13b_v1",
+    outputs=gr.outputs.Textbox(label="Generated Text"),
+    title="GPT-4 Text Generation",
 ).launch()