changed a section in app.py and added the requirements.txt

app.py

@@ -1,31 +1,38 @@
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from peft import PeftModel
-import gradio as gr
-
-BASE_MODEL = "PartAI/Dorna-Llama3-8B-Instruct"
-LORA_PATH = "./dorna-diabetes-finetuned"  # این پوشه رو آپلود می‌کنی توی اسپیس
-
-tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
-
-base_model = AutoModelForCausalLM.from_pretrained(
-    BASE_MODEL,
-    device_map="auto",
-    torch_dtype=torch.float16,
-)
-
-model = PeftModel.from_pretrained(base_model, LORA_PATH)
-
-def generate_response(prompt):
-    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
-    with torch.no_grad():
-        output = model.generate(
-            input_ids=input_ids,
-            max_new_tokens=200,
-            do_sample=True,
-            temperature=0.7,
-            top_p=0.9,
-        )
-    return tokenizer.decode(output[0], skip_special_tokens=True)
-
-gr.Interface(fn=generate_response, inputs="text", outputs="text", title="Dorna-Llama3 LoRA").launch()
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import gradio as gr
+import os
+import zipfile
+
+if not os.path.exists("dorna-diabetes-finetuned"):
+    with zipfile.ZipFile("dorna-diabetes-finetuned.zip", "r") as zip_ref:
+        zip_ref.extractall(".")
+    print("✅ فایل ZIP اکسترکت شد.")
+
+BASE_MODEL = "PartAI/Dorna-Llama3-8B-Instruct"
+LORA_PATH = "./dorna-diabetes-finetuned"  # این پوشه رو آپلود می‌کنی توی اسپیس
+
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    device_map="auto",
+    torch_dtype=torch.float16,
+)
+
+model = PeftModel.from_pretrained(base_model, LORA_PATH)
+
+def generate_response(prompt):
+    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
+    with torch.no_grad():
+        output = model.generate(
+            input_ids=input_ids,
+            max_new_tokens=200,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9,
+        )
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+gr.Interface(fn=generate_response, inputs="text", outputs="text", title="Dorna-Llama3 LoRA").launch()

requirements.txt

@@ -0,0 +1,6 @@
+transformers
+peft
+accelerate
+torch
+bitsandbytes
+gradio