Here is full step by step demo of how to install code llama by Meta on your local server in cloud or on laptop easily and quickly.

Commands Used:

!pip install transformers

!git clone https://github.com/PanQiWei/AutoGPTQ

cd AutoGPTQ

! git checkout a7167b1

!pip3 install .

from transformers import AutoTokenizer, pipeline, logging

from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

model_name_or_path = "TheBloke/CodeLlama-7B-GPTQ"

use_triton = False

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,

        use_safetensors=True,

        trust_remote_code=False,

        device="cuda:0",

        use_triton=use_triton,

        quantize_config=None)

prompt = "Write a bash script to delete all files older than 90 days with extension .log"

prompt_template=f'''{prompt}

'''

print("\ \ *** Generate:")

logging.set_verbosity(logging.CRITICAL)

print("*** Pipeline:")

pipe = pipeline(

    "text-generation",

    model=model,

    tokenizer=tokenizer,

    max_new_tokens=512,

    temperature=0.7,

    top_p=0.95,

    repetition_penalty=1.15

)

print(pipe(prompt_template)[0]['generated_text'])