Spaces:
Sleeping
Sleeping
File size: 3,450 Bytes
5fdb69e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
from pathlib import Path
import modal
ROOT_PATH = Path(__file__).parent.parent
image = (
modal.Image.debian_slim()
.pip_install("pytest")
.pip_install_from_requirements(ROOT_PATH / "requirements.txt")
)
app = modal.App("pricer-ci-testing", image=image)
# mount: add local files to the remote container
tests = modal.Mount.from_local_dir(ROOT_PATH / "tests", remote_path="/root/tests")
@app.function(gpu="any", mounts=[tests])
def pytest():
import subprocess
subprocess.run(["pytest", "-vs"], check=True, cwd="/root")
secrets = [modal.Secret.from_name("huggingface-secret")]
# Constants
GPU = "T4"
BASE_MODEL = "meta-llama/Meta-Llama-3.1-8B"
PROJECT_NAME = "pricer"
HF_USER = "ed-donner" # your HF name here! Or use mine if you just want to reproduce my results.
RUN_NAME = "2024-09-13_13.04.39"
PROJECT_RUN_NAME = f"{PROJECT_NAME}-{RUN_NAME}"
REVISION = "e8d637df551603dc86cd7a1598a8f44af4d7ae36"
FINETUNED_MODEL = f"{HF_USER}/{PROJECT_RUN_NAME}"
MODEL_DIR = "hf-cache/"
BASE_DIR = MODEL_DIR + BASE_MODEL
FINETUNED_DIR = MODEL_DIR + FINETUNED_MODEL
QUESTION = "How much does this cost to the nearest dollar?"
PREFIX = "Price is $"
class Pricer:
def download_model_to_folder(self):
from huggingface_hub import snapshot_download
import os
os.makedirs(MODEL_DIR, exist_ok=True)
print(f"Using this HF Token: {hf_token}")
snapshot_download(BASE_MODEL, local_dir=BASE_DIR, use_auth_token=hf_token)
snapshot_download(FINETUNED_MODEL, revision=REVISION, local_dir=FINETUNED_DIR, use_auth_token=hf_token)
def setup(self):
import os
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_DIR)
self.tokenizer.pad_token = self.tokenizer.eos_token
self.tokenizer.padding_side = "right"
self.base_model = AutoModelForCausalLM.from_pretrained(
BASE_DIR,
quantization_config=quant_config,
device_map="auto"
)
self.fine_tuned_model = PeftModel.from_pretrained(self.base_model, FINETUNED_DIR, revision=REVISION)
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
def wake_up(self) -> str:
return "ok"
|