Create app.py

app.py

@@ -0,0 +1,55 @@
+import torch
+from transformers import LlamaForCausalLM, LlamaTokenizer, pipeline
+from peft import  PeftModel
+import re
+import gradio as gr
+
+tokenizer = LlamaTokenizer.from_pretrained('mostafaamiri/persian_llama_7b')
+
+base_model = LlamaForCausalLM.from_pretrained(
+    "meta-llama/Llama-2-7b-hf",
+    load_in_8bit=False,
+    )
+base_model.resize_token_embeddings(len(tokenizer))
+
+model = PeftModel.from_pretrained(
+    base_model, 
+    "mostafaamiri/persian_llama_7b",)
+
+
+prompt_input = (
+    "Below is an instruction that describes a task. "
+    "Write a response that appropriately completes the request.\n\n"
+    "### Instruction:\n\n{instruction}\n\n### Response:\n\n"
+)
+
+
+def generate_prompt(instruction, input=None):
+    if input:
+        instruction = instruction + '\n' + input
+    return prompt_input.format_map({'instruction': instruction})
+config=dict(
+    temperature=0.2,
+    top_k=40,
+    top_p=0.9,
+    do_sample=True,
+    num_beams=1,
+    repetition_penalty=1.2,
+    max_new_tokens=300
+    )
+
+
+def launch_model(text):
+
+    sample_data = [text]
+    inputToken = tokenizer(generate_prompt(sample_data) , return_tensors="pt")
+
+    outputs = model.generate(**inputToken, **config)
+    output = tokenizer.decode(outputs[0],skip_special_tokens=True)
+    output = re.sub(r"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n\n\[.*\]\n\n### Response:\n\n", "", output)
+
+    return output
+
+
+iface = gr.Interface(fn=launch_model, inputs="text", outputs="text")
+iface.launch()