From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
67 lines
2.2 KiB
67 lines
2.2 KiB
import modal |
|
from modal import App, Image |
|
|
|
# Setup |
|
|
|
app = modal.App("pricer") |
|
image = Image.debian_slim().pip_install("torch", "transformers", "bitsandbytes", "accelerate", "peft") |
|
secrets = [modal.Secret.from_name("hf-secret")] |
|
|
|
# Constants |
|
|
|
GPU = "T4" |
|
BASE_MODEL = "meta-llama/Meta-Llama-3.1-8B" |
|
PROJECT_NAME = "pricer" |
|
HF_USER = "cproSD" # your HF name here! Or use mine if you just want to reproduce my results. |
|
RUN_NAME = "2025-04-08_21.52.37" |
|
PROJECT_RUN_NAME = f"{PROJECT_NAME}-{RUN_NAME}" |
|
#DEL: REVISION = "e8d637df551603dc86cd7a1598a8f44af4d7ae36" |
|
FINETUNED_MODEL = f"{HF_USER}/{PROJECT_RUN_NAME}" |
|
|
|
|
|
@app.function(image=image, secrets=secrets, gpu=GPU, timeout=1800) |
|
def price(description: str) -> float: |
|
import os |
|
import re |
|
import torch |
|
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, set_seed |
|
from peft import PeftModel |
|
|
|
QUESTION = "How much does this cost to the nearest dollar?" |
|
PREFIX = "Price is $" |
|
|
|
prompt = f"{QUESTION}\n{description}\n{PREFIX}" |
|
|
|
# Quant Config |
|
quant_config = BitsAndBytesConfig( |
|
load_in_4bit=True, |
|
bnb_4bit_use_double_quant=True, |
|
bnb_4bit_compute_dtype=torch.bfloat16, |
|
bnb_4bit_quant_type="nf4" |
|
) |
|
|
|
# Load model and tokenizer |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) |
|
tokenizer.pad_token = tokenizer.eos_token |
|
tokenizer.padding_side = "right" |
|
|
|
base_model = AutoModelForCausalLM.from_pretrained( |
|
BASE_MODEL, |
|
quantization_config=quant_config, |
|
device_map="auto" |
|
) |
|
|
|
#DEL: fine_tuned_model = PeftModel.from_pretrained(base_model, FINETUNED_MODEL, revision=REVISION) |
|
fine_tuned_model = PeftModel.from_pretrained(base_model, FINETUNED_MODEL) |
|
|
|
set_seed(42) |
|
inputs = tokenizer.encode(prompt, return_tensors="pt").to("cuda") |
|
attention_mask = torch.ones(inputs.shape, device="cuda") |
|
outputs = fine_tuned_model.generate(inputs, attention_mask=attention_mask, max_new_tokens=5, num_return_sequences=1) |
|
result = tokenizer.decode(outputs[0]) |
|
|
|
contents = result.split("Price is $")[1] |
|
contents = contents.replace(',','') |
|
match = re.search(r"[-+]?\d*\.\d+|\d+", contents) |
|
return float(match.group()) if match else 0
|
|
|