Create app.py

app.py

@@ -0,0 +1,24 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import LoraConfig, get_peft_model
+import torch
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("youssef227/llama-3-8b-Instruct-bnb-telcom-3", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("youssef227/llama-3-8b-Instruct-bnb-telcom-3", trust_remote_code=True)
+
+
+def generator(text):
+  inputs = tokenizer(
+  [
+      alpaca_prompt.format(
+          f" {context}انت ممثل خدمة العملاء لدى شركة فودافون.و دي معلومات ممكن تفيدك", # instruction
+          text, # input
+          "", # output - leave this blank for generation!
+      )
+  ], return_tensors = "pt").to("cuda")
+  outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
+  return tokenizer.batch_decode(outputs)
+text = st.text_area('enter some text!')
+if text:
+  out = generator(text)
+  st.json(out)