File size: 1,451 Bytes
45a9357 |
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 |
# ---
# args: ["--force-download"]
# ---
import modal
MODELS_DIR = "/llamas"
DEFAULT_NAME = "meta-llama/Meta-Llama-3.1-8B-Instruct"
DEFAULT_REVISION = "8c22764a7e3675c50d4c7c9a4edb474456022b16"
volume = modal.Volume.from_name("llamas", create_if_missing=True)
image = (
modal.Image.debian_slim(python_version="3.10")
.pip_install(
[
"huggingface_hub", # download models from the Hugging Face Hub
"hf-transfer", # download models faster with Rust
]
)
.env({"HF_HUB_ENABLE_HF_TRANSFER": "1"})
)
MINUTES = 60
HOURS = 60 * MINUTES
app = modal.App(
image=image, secrets=[modal.Secret.from_name("huggingface-secret")]
)
@app.function(volumes={MODELS_DIR: volume}, timeout=4 * HOURS)
def download_model(model_name, model_revision, force_download=False):
from huggingface_hub import snapshot_download
volume.reload()
snapshot_download(
model_name,
local_dir=MODELS_DIR + "/" + model_name,
ignore_patterns=[
"*.pt",
"*.bin",
"*.pth",
"original/*",
], # Ensure safetensors
revision=model_revision,
force_download=force_download,
)
volume.commit()
@app.local_entrypoint()
def main(
model_name: str = DEFAULT_NAME,
model_revision: str = DEFAULT_REVISION,
force_download: bool = False,
):
download_model.remote(model_name, model_revision, force_download) |