app.py

import gradio as gr
from langchain.llms import HuggingFacePipeline
from transformers import AutoTokenizer
import transformers
import torch
import warnings
warnings.filterwarnings('ignore')

# llm = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q3_K_S.bin")

tokenizer=AutoTokenizer.from_pretrained(model="TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q3_K_S.bin")

pipeline=transformers.pipeline(
    "text-generation",
    model=(model="TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q3_K_S.bin"),
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
    max_length=500,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id
    )

llm=HuggingFacePipeline(pipeline=pipeline, model_kwargs={'temperature':0})

def greet(prompt):
    
    
    return llm(prompt)



iface = gr.Interface(fn=greet, inputs="text", outputs="text")
iface.launch()