app.py

import torch
from peft import PeftModel
import transformers
import gradio as gr

assert (
    "LlamaTokenizer" in transformers._import_structure["models.llama"]
), "LLaMA is now in HuggingFace's main branch.\nPlease reinstall it: pip uninstall transformers && pip install git+https://github.com/huggingface/transformers.git"
from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig

tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-7b-hf")

BASE_MODEL = "TheBloke/vicuna-7B-1.1-HF"
LORA_WEIGHTS = "RinInori/vicuna_finetuned_6_sentiments" #Fine-tuned Alpaca model for sentiment analysis

if torch.cuda.is_available():
    device = "cuda"
else:
    device = "cpu"
try:
    if torch.backends.mps.is_available():
        device = "mps"
except:
    pass

if device == "cuda":
    model = LlamaForCausalLM.from_pretrained(
        BASE_MODEL,
        load_in_8bit=False,
        torch_dtype=torch.float16,
        device_map="auto",
    )
    model = PeftModel.from_pretrained(
        model, LORA_WEIGHTS, torch_dtype=torch.float16, force_download=True
    )
elif device == "mps":
    model = LlamaForCausalLM.from_pretrained(
        BASE_MODEL,
        device_map={"": device},
        torch_dtype=torch.float16,
    )
    model = PeftModel.from_pretrained(
        model,
        LORA_WEIGHTS,
        device_map={"": device},
        torch_dtype=torch.float16,
    )
else:
    model = LlamaForCausalLM.from_pretrained(
        BASE_MODEL, device_map={"": device}, low_cpu_mem_usage=True
    )
    model = PeftModel.from_pretrained(
        model,
        LORA_WEIGHTS,
        device_map={"": device},
    )

if device != "cpu":
    model.half()
model.eval()
if torch.__version__ >= "2":
    model = torch.compile(model)

def evaluate(
    input_text,
    temperature=0.1,
    top_p=0.75,
    top_k=40,
    num_beams=4,
    max_new_tokens=128,
    **kwargs,
):
    prompt = input_text
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"].to(device)
    generation_config = GenerationConfig(
        temperature=temperature,
        top_p=top_p,
        top_k=top_k,
        num_beams=num_beams,
        **kwargs,
    )
    with torch.no_grad():
        generation_output = model.generate(
            input_ids=input_ids,
            generation_config=generation_config,
            return_dict_in_generate=True,
            output_scores=True,
            max_new_tokens=max_new_tokens,
        )
    s = generation_output.sequences[0]
    output = tokenizer.decode(s)
    return output.strip()

g = gr.Interface(
    fn=evaluate,
    inputs=gr.inputs.Textbox(label="Input", placeholder="Type your input here..."),
    outputs=gr.outputs.Textbox(label="Output"),
    title="ChatBot and Text Generation",
    description="This model is a fine-tuned version of the Vicuna model. \
    BASE MODEL is 'TheBloke/vicuna-7B-1.1-HF', and LORA_WEIGHTS = 'RinInori/vicuna_finetuned_6_sentiments' ",    
    theme="default",
)

if __name__ == "__main__":
    g.launch()