update app.py

app.py

@@ -2,42 +2,22 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 from gpt4all import GPT4All
+import os
 
-model = GPT4All("wizardlm-13b-v1.1-superhot-8k.ggmlv3.q4_0.bin")
+# Specify the local path to the downloaded model file
+model_path = "path/to/wizardlm-13b-v1.1-superhot-8k.ggmlv3.q4_0.bin"
 
-# model = AutoModelForCausalLM.from_pretrained(
-#     "tiiuae/falcon-7b-instruct",
-#     torch_dtype=torch.bfloat16,
-#     trust_remote_code=True,
-#     device_map="auto",
-#     low_cpu_mem_usage=True,
-# )
-# tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct")
+# Check if the model file exists locally
+if not os.path.exists(model_path):
+    raise FileNotFoundError(f"Model file not found at {model_path}. Please download it manually.")
 
+# Initialize the GPT4All model
+model = GPT4All(model_path)
 
 def generate_text(input_text):
-    # input_ids = tokenizer.encode(input_text, return_tensors="pt")
-    # attention_mask = torch.ones(input_ids.shape)
-
-    output = model.generate(
-        input_text
-        # input_ids,
-        # attention_mask=attention_mask,
-        # max_length=200,
-        # do_sample=True,
-        # top_k=10,
-        # num_return_sequences=1,
-        # eos_token_id=tokenizer.eos_token_id,
-    )
-
-    # output_text = tokenizer.decode(output[0], skip_special_tokens=True)
-    # print(output_text)
-
-    # Remove Prompt Echo from Generated Text
-    # cleaned_output_text = output_text.replace(input_text, "")
+    output = model.generate(input_text)
     return output
 
-
 text_generation_interface = gr.Interface(
     fn=generate_text,
     inputs=[
@@ -45,4 +25,4 @@ text_generation_interface = gr.Interface(
     ],
     outputs=gr.inputs.Textbox(label="Generated Text"),
     title="Falcon-7B Instruct",
-).launch()
+).launch()