# Loadb     checkpoint shards:       0%|StatTerra | 0/3[00:00<00:00,           Loading checkpoint shards:  33%|███▎      | 1/3 [00:01<00:03,  1.75s/it]Loading checkpoint shards:  67%|██████▋   | 2/3 [00:03<00:01,  1.72s/it]Loading checkpoint shards: 100%|██████████| 3/3 [00:04<00:00,  1.64s/it]Loading checkpoint shards: 100%|██████████| 3/3 [00:04<00:00,  1.66s/it]
      load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
 import
tokenizer = AutoTokenizer.from_pretrained("m-a-p/ChatMusician-Base")
model = AutoModelForCausalLM.from_pretrained("m-a-p/ChatMusician-Base")
    
    # Use a pipeline as a high-level helper
from transformers import pipeline


    pipe = pipeline("text-generation", model="m-a-p/ChatMusician-Base")

from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_NAME = 'NousResearch/Genstruct-7B'

model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda', load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
    
    import sagemaker
import boto3
from sagemaker.huggingface import HuggingFace

try:
	role = sagemaker.get_execution_role()
except ValueError:
	iam = boto3.client('iam')
	role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']
		
hyperparameters = {
	'model_name_or_path':'m-a-p/ChatMusician-Base',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.37.0/examples/pytorch/seq2seq
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.37.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_translation.py',
	source_dir='./examples/pytorch/seq2seq',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.37.0',
	pytorch_version='2.1.0',
	py_version='py310',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
	         }

     }


}