app.py

from langchain_community.llms.ctransformers import CTransformers
import os 
import gradio as gr

hf_token = os.environ.get('HF_TOKEN')

from huggingface_hub import login
login(token=hf_token)


# config = AutoConfig.from_pretrained("Mistral-7B-v0.1-GGUF")
# config.config.max_new_tokens = 2000
# config.config.context_length = 6000

# llm = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-v0.1-GGUF", model_file="mistral-7b-v0.1.Q5_K_M.gguf", model_type="mistral",gpu_layers=0, config=config)

MODEL_TYPE = 'mistral'
MODEL_BIN_PATH =  "mistral-7b-instruct-v0.1.Q3_K_S.gguf"
MAX_NEW_TOKEN =  600
TEMPRATURE =  0.01
CONTEXT_LENGTH =   6000


llm = CTransformers(
            model=MODEL_BIN_PATH,
            config={
                'max_new_tokens': MAX_NEW_TOKEN,
                'temperature': TEMPRATURE,
                'context_length': CONTEXT_LENGTH
            },
            model_type=MODEL_TYPE
        )

def generate_text(input_text):


    output = llm(input_text)
    print(output)
    return output


text_generation_interface = gr.Interface(
    fn=generate_text,
    inputs="text", outputs="text")
text_generation_interface.launch()