app.py

# import gradio as gr
# from transformers import AutoModelForCausalLM, AutoTokenizer

# from gpt4all import GPT4All
# model = GPT4All("wizardlm-13b-v1.1-superhot-8k.ggmlv3.q4_0.bin")

#----------------------------------------------------------------------------------------------------------------------------
from transformers import AutoModelForCausalLM, AutoTokenizer

# Path to the model directory (assuming it's in the same directory as your script)
model_directory = "./"

# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained(model_directory, from_tf=True)
tokenizer = AutoTokenizer.from_pretrained(model_directory, trust_remote_code=True)

# Now you can generate text as before
# prompt = "What is a large language model?"
# input_ids = tokenizer.encode(prompt, return_tensors="pt")

# output = model.generate(input_ids, max_length=200, num_return_sequences=1)
# generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
# print(generated_text)

# ---------------------------------------------------------------------------------------------------------------------------------------------------------------------
# Ignore warnings
logging.set_verbosity(logging.CRITICAL)

# Run text generation pipeline with our next model
# prompt = "What is a large language model?"
# pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
# result = pipe(f"<s>[INST] {prompt} [/INST]")
# print(result[0]['generated_text'])

#---------------------------------------------------------------------------------------------------------------------------------------------------------------------
# Ignore warnings
# logging.set_verbosity(logging.CRITICAL)

# Run text generation pipeline with our next model
# prompt = "What is a large language model?"
# pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
# result = pipe(f"<s>[INST] {prompt} [/INST]")
# print(result[0]['generated_text'])


def generate_text(prompt):
    # output = model.generate(input_text)
    # pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
    # result = pipe(f"<s>[INST] {prompt} [/INST]")
    # prompt = "What is a large language model?"
    input_ids = tokenizer.encode(prompt, return_tensors="pt")

    output = model.generate(input_ids, max_length=200, num_return_sequences=1)
    result = tokenizer.decode(output[0], skip_special_tokens=True)
    return result

text_generation_interface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.inputs.Textbox(label="Input Text"),
    ],
    outputs=gr.outputs.Textbox(label="Generated Text"),
    title="GPT-4 Text Generation",
).launch()



# model_name = ""