git clone https://github.com/facebookresearch/llama.git

bash download.sh

pip install git+https://github.com/huggingface/transformerscd transformerspython convert_llama_weights_to_hf.py \    --input_dir /path/to/downloaded/llama/weights --model_size 7B --output_dir models_hf/7B

git clone https://github.com/facebookresearch/llama-recipes.git

pip install 
jupyterlabjupyter lab # in the repo you want to work in

model_id="./models_hf/7B"

import torch
from transformers import LlamaForCausalLM, LlamaTokenizer
from peft import PeftModel, PeftConfig

model_id="./models_hf/7B"
tokenizer = LlamaTokenizer.from_pretrained(model_id)
model =LlamaForCausalLM.from_pretrained(model_id, load_in_8bit=True, device_map='auto', torch_dtype=torch.float16)

model = PeftModel.from_pretrained(model, "/root/llama-recipes/samsungsumarizercheckpoint")

eval_prompt = """
Summarize this dialog:
A: Hi Tom, are you busy tomorrow’s afternoon?
B: I’m pretty sure I am. What’s up?
A: Can you go with me to the animal shelter?.
B: What do you want to do?
A: I want to get a puppy for my son.
B: That will make him so happy.
A: Yeah, we’ve discussed it many times. I think he’s ready now.
B: That’s good. Raising a dog is a tough issue. Like having a baby ;-)
A: I'll get him one of those little dogs.
B: One that won't grow up too big;-)A: And eat too much;-))
B: Do you know which one he would like?
A: Oh, yes, I took him there last Monday. He showed me one that he really liked.
B: I bet you had to drag him away.
A: He wanted to take it home right away ;-).
B: I wonder what he'll name it.
A: He said he’d name it after his dead hamster – Lemmy  - he's  a great Motorhead fan :-)))
---
Summary:
"""


model_input = tokenizer(eval_prompt, return_tensors="pt").to("cuda")


model.eval()
with torch.no_grad():    
    print(tokenizer.decode(model.generate(**model_input, max_new_tokens=100)[0], skip_special_tokens=True))

from llmengine import FineTune
response = FineTune.create(
    model="llama-2-7b",
    training_file="s3://my-bucket/path/to/training-file.csv",
)


print(response.json())

pip install datasets==2.13.1 smart_open[s3]==5.2.1 pandas==1.4.4

from datasets import load_dataset
from smart_open import smart_open
import pandas as pd


dataset = load_dataset('derek-thomas/ScienceQA')
dataset['train'].features

Context: A baby wants to know what is inside of a cabinet. Her hand applies a force to the door, and the door opens.
Question: Which type of force from the baby's hand opens the cabinet door?
Options: (A) pull (B) push
Answer: A.

choice_prefixes = [chr(ord('A') + i) for i in range(26)] # A-Z
def format_options(options, choice_prefixes):
    return ' '.join([f'({c}) {o}' for c, o in zip(choice_prefixes, options)])

def format_prompt(r, choice_prefixes):
    options = format_options(r['choices'], choice_prefixes)
    return f'''Context: {r["hint"]}\nQuestion: {r["question"]}\nOptions:{options}\nAnswer:'''


def format_response(r, choice_prefixes):
return choice_prefixes[r['answer']]

def convert_dataset(ds):
    prompts = [format_prompt(i, choice_prefixes) for i in ds if i['hint'] != '']
    labels = [format_response(i, choice_prefixes) for i in ds if i['hint'] != '']
    df = pd.DataFrame.from_dict({'prompt': prompts, 'response': labels})
    return df

train_url = 's3://...'
val_url = 's3://...'
df_train = convert_dataset(dataset['train'])
with smart_open(train_url, 'wb') as f:
    df_train.to_csv(f)
df_val = convert_dataset(dataset['validation'])
with smart_open(val_url, 'wb') as f:
df_val.to_csv(f)

pip install scale-llm-engine

import os
os.environ['SCALE_API_KEY'] = 'xxx'

from llmengine import FineTune
response = FineTune.create(
    model="llama-2-7b",
    training_file=train_url,
    validation_file=val_url,
    hyperparameters={
        'lr':2e-4,
    },
    suffix='science-qa-llama'
)
run_id = response.fine_tune_id

while True:
    job_status = FineTune.get(run_id).status
    # Returns one of `PENDING`, `STARTED`, `SUCCESS`, `RUNNING`,
    # `FAILURE`, `CANCELLED`, `UNDEFINED` or `TIMEOUT`
    print(job_status)
    if job_status == 'SUCCESS':
        break
    time.sleep(60)
#Logs for completed or running jobs can be fetched with
logs = FineTune.get_events(run_id)

ft_model = FineTune.get(run_id).fine_tuned_model

import pandas as pd


#Helper a function to get outputs for fine-tuned model with retries
def get_output(prompt: str, num_retry: int = 5):
    for _ in range(num_retry):
    try:
    response = Completion.create(
        model=ft_model, 
        prompt=prompt, 
        max_new_tokens=1, 
        temperature=0.01
      )
      return response.output.text.strip()
    except Exception as e:
      print(e)
  return ""


#Read the test data
test = pd.read_csv(val_url)


test["prediction"] = test["prompt"].apply(get_output)
print(f"Accuracy: {(test['response'] == test['prediction']).mean() * 100:.2f}%")