Update app.py

app.py

@@ -2,6 +2,11 @@ import torch
 from peft import PeftModel
 import transformers
 import gradio as gr
+from fastapi import FastAPI
+import random
+
+
+app= FastAPI()
 
 assert (
     "LlamaTokenizer" in transformers._import_structure["models.llama"]
@@ -57,7 +62,8 @@ else:
     )
 
 
-def generate_prompt(instruction, input=None):
+def generate_prompt(input=None):
+    instruction= '''You are a dating bio writer for single boy with the keywords provided. the dating bio should be within 30 words and should be catchy. the dating bio should be different in every run.'''
     if input:
         return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 
@@ -67,14 +73,7 @@ def generate_prompt(instruction, input=None):
 ### Input:
 {input}
 
-### Response:"""
-    else:
-        return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
-
-### Instruction:
-{instruction}
-
-### Response:"""
+# ### Response:"""
 
 if device != "cpu":
     model.half()
@@ -82,22 +81,23 @@ model.eval()
 if torch.__version__ >= "2":
     model = torch.compile(model)
 
-
-def evaluate(
-    instruction,
-    input=None,
-    temperature=0.1,
+@app.post("/generate_bio")
+async def evaluate(
+    input:str,
+    temperature=[0.2, 0.5, 0.7, 0.9, 1.0],
     top_p=0.75,
     top_k=40,
     num_beams=4,
     max_new_tokens=128,
+    seed=None,
+    do_sample=True,
     **kwargs,
 ):
-    prompt = generate_prompt(instruction, input)
+    prompt = generate_prompt(input)
     inputs = tokenizer(prompt, return_tensors="pt")
     input_ids = inputs["input_ids"].to(device)
     generation_config = GenerationConfig(
-        temperature=temperature,
+        temperature=random.choice(temperature),
         top_p=top_p,
         top_k=top_k,
         num_beams=num_beams,
@@ -110,56 +110,13 @@ def evaluate(
             return_dict_in_generate=True,
             output_scores=True,
             max_new_tokens=max_new_tokens,
+            seed=None,
+            do_sample= do_sample
         )
     s = generation_output.sequences[0]
     output = tokenizer.decode(s)
     return output.split("### Response:")[1].strip()
 
-
-g = gr.Interface(
-    fn=evaluate,
-    inputs=[
-        gr.components.Textbox(
-            lines=2, label="Instruction", placeholder="Tell me about alpacas."
-        ),
-        gr.components.Textbox(lines=2, label="Input", placeholder="none"),
-        gr.components.Slider(minimum=0, maximum=1, value=0.1, label="Temperature"),
-        gr.components.Slider(minimum=0, maximum=1, value=0.75, label="Top p"),
-        gr.components.Slider(minimum=0, maximum=100, step=1, value=40, label="Top k"),
-        gr.components.Slider(minimum=1, maximum=4, step=1, value=4, label="Beams"),
-        gr.components.Slider(
-            minimum=1, maximum=512, step=1, value=128, label="Max tokens"
-        ),
-    ],
-    outputs=[
-        gr.inputs.Textbox(
-            lines=5,
-            label="Output",
-        )
-    ],
-    title="🦙🌲 Alpaca-LoRA",
-    description="Alpaca-LoRA is a 7B-parameter LLaMA model finetuned to follow instructions. It is trained on the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset and makes use of the Huggingface LLaMA implementation. For more information, please visit [the project's website](https://github.com/tloen/alpaca-lora).",
-)
-g.queue(concurrency_count=1)
-g.launch()
-
-# Old testing code follows.
-
-"""
 if __name__ == "__main__":
-    # testing code for readme
-    for instruction in [
-        "Tell me about alpacas.",
-        "Tell me about the president of Mexico in 2019.",
-        "Tell me about the king of France in 2019.",
-        "List all Canadian provinces in alphabetical order.",
-        "Write a Python program that prints the first 10 Fibonacci numbers.",
-        "Write a program that prints the numbers from 1 to 100. But for multiples of three print 'Fizz' instead of the number and for the multiples of five print 'Buzz'. For numbers which are multiples of both three and five print 'FizzBuzz'.",
-        "Tell me five words that rhyme with 'shock'.",
-        "Translate the sentence 'I have no mouth but I must scream' into Spanish.",
-        "Count up from 1 to 500.",
-    ]:
-        print("Instruction:", instruction)
-        print("Response:", evaluate(instruction))
-        print()
-"""
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)