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.
 
 

87 lines
3.1 KiB

import modal
from modal import App, Volume, Image
# Setup - define our infrastructure with code!
app = modal.App("pricer-service")
image = Image.debian_slim().pip_install("huggingface", "torch", "transformers", "bitsandbytes", "accelerate", "peft")
image.add_local_python_source("hello", "llama") #CP: adding here based on Deprecation warnings...
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}"
FINETUNED_MODEL = f"{HF_USER}/{PROJECT_RUN_NAME}"
#DEL: MODEL_DIR = "/models/"
#DEL: BASE_DIR = MODEL_DIR + BASE_MODEL
#DEL: FINETUNED_DIR = MODEL_DIR + FINETUNED_MODEL
CACHE_DIR = "/cache" #CP: Use the standard /cache path for hf-hub-cache
QUESTION = "How much does this cost to the nearest dollar?"
PREFIX = "Price is $"
#CP: Use the pre-configured hf-hub-cache Volume...
hf_cache_volume = Volume.from_name("hf-hub-cache")
@app.cls(
image=image.env({"HF_HUB_CACHE": CACHE_DIR}),
secrets=secrets,
gpu=GPU,
timeout=1800,
volumes={CACHE_DIR: hf_cache_volume}
)
class Pricer:
@modal.enter()
def setup(self):
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, set_seed
from peft import PeftModel
# 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
self.tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
self.tokenizer.pad_token = self.tokenizer.eos_token
self.tokenizer.padding_side = "right"
self.base_model = AutoModelForCausalLM.from_pretrained(
BASE_MODEL,
quantization_config=quant_config,
device_map="auto"
)
self.fine_tuned_model = PeftModel.from_pretrained(self.base_model, FINETUNED_MODEL)
@modal.method()
def price(self, description: str) -> float:
import os
import re
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, set_seed
from peft import PeftModel
set_seed(42)
prompt = f"{QUESTION}\n\n{description}\n\n{PREFIX}"
inputs = self.tokenizer.encode(prompt, return_tensors="pt").to("cuda")
attention_mask = torch.ones(inputs.shape, device="cuda")
outputs = self.fine_tuned_model.generate(inputs, attention_mask=attention_mask, max_new_tokens=5, num_return_sequences=1)
result = self.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
@modal.method()
def wake_up(self) -> str:
return "ok"