Using llama 13b model from huggingface

llama.py

from torch import cuda, bfloat16
from langchain.llms import HuggingFacePipeline
import transformers

model_id = 'meta-llama/Llama-2-13b-chat-hf'

device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'

# set quantization configuration to load large model with less GPU memory
# this requires the `bitsandbytes` library
bnb_config = transformers.BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type='nf4',
    bnb_4bit_use_double_quant=True,
    bnb_4bit_compute_dtype=bfloat16
)

# begin initializing HF items, need auth token for these
hf_auth = 'your_hugging_face_token'
model_config = transformers.AutoConfig.from_pretrained(
    model_id,
    use_auth_token=hf_auth
)

model = transformers.AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    config=model_config,
    quantization_config=bnb_config,
    device_map='auto',
    use_auth_token=hf_auth
)
model.eval()
print(f"Model loaded on {device}")

generate_text = transformers.pipeline(
    model=model, tokenizer=tokenizer,
    return_full_text=True,  # langchain expects the full text
    task='text-generation',
    # we pass model parameters here too
    temperature=0.0,  # 'randomness' of outputs, 0.0 is the min and 1.0 the max
    max_new_tokens=512,  # mex number of tokens to generate in the output
    repetition_penalty=1.1  # without this output begins repeating
)

llm = HuggingFacePipeline(pipeline=generate_text)

llm(prompt="What is the capital of India?")