
* feat: adding new vlm-models support Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the transformers Signed-off-by: Peter Staar <taa@zurich.ibm.com> * got microsoft/Phi-4-multimodal-instruct to work Signed-off-by: Peter Staar <taa@zurich.ibm.com> * working on vlm's Signed-off-by: Peter Staar <taa@zurich.ibm.com> * refactoring the VLM part Signed-off-by: Peter Staar <taa@zurich.ibm.com> * all working, now serious refacgtoring necessary Signed-off-by: Peter Staar <taa@zurich.ibm.com> * refactoring the download_model Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added the formulate_prompt Signed-off-by: Peter Staar <taa@zurich.ibm.com> * pixtral 12b runs via MLX and native transformers Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added the VlmPredictionToken Signed-off-by: Peter Staar <taa@zurich.ibm.com> * refactoring minimal_vlm_pipeline Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the MyPy Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added pipeline_model_specializations file Signed-off-by: Peter Staar <taa@zurich.ibm.com> * need to get Phi4 working again ... Signed-off-by: Peter Staar <taa@zurich.ibm.com> * finalising last points for vlms support Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the pipeline for Phi4 Signed-off-by: Peter Staar <taa@zurich.ibm.com> * streamlining all code Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatted the code Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixing the tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added the html backend to the VLM pipeline Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the static load_from_doctags Signed-off-by: Peter Staar <taa@zurich.ibm.com> * restore stable imports Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use AutoModelForVision2Seq for Pixtral and review example (including rename) Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * remove unused value Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * refactor instances of VLM models Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * skip compare example in CI Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use lowercase and uppercase only Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add new minimal_vlm example and refactor pipeline_options_vlm_model for cleaner import Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * rename pipeline_vlm_model_spec Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * move more argument to options and simplify model init Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add supported_devices Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * remove not-needed function Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * exclude minimal_vlm Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * missing file Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add message for transformers version Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * rename to specs Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use module import and remove MLX from non-darwin Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * remove hf_vlm_model and add extra_generation_args Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use single HF VLM model class Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * remove torch type Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add docs for vision models Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
123 lines
3.9 KiB
Python
123 lines
3.9 KiB
Python
import logging
|
|
from pathlib import Path
|
|
from typing import Optional
|
|
|
|
from docling.datamodel.pipeline_options import (
|
|
granite_picture_description,
|
|
smolvlm_picture_description,
|
|
)
|
|
from docling.datamodel.settings import settings
|
|
from docling.datamodel.vlm_model_specs import (
|
|
SMOLDOCLING_MLX,
|
|
SMOLDOCLING_TRANSFORMERS,
|
|
)
|
|
from docling.models.code_formula_model import CodeFormulaModel
|
|
from docling.models.document_picture_classifier import DocumentPictureClassifier
|
|
from docling.models.easyocr_model import EasyOcrModel
|
|
from docling.models.layout_model import LayoutModel
|
|
from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
|
|
from docling.models.table_structure_model import TableStructureModel
|
|
from docling.models.utils.hf_model_download import download_hf_model
|
|
|
|
_log = logging.getLogger(__name__)
|
|
|
|
|
|
def download_models(
|
|
output_dir: Optional[Path] = None,
|
|
*,
|
|
force: bool = False,
|
|
progress: bool = False,
|
|
with_layout: bool = True,
|
|
with_tableformer: bool = True,
|
|
with_code_formula: bool = True,
|
|
with_picture_classifier: bool = True,
|
|
with_smolvlm: bool = False,
|
|
with_smoldocling: bool = False,
|
|
with_smoldocling_mlx: bool = False,
|
|
with_granite_vision: bool = False,
|
|
with_easyocr: bool = True,
|
|
):
|
|
if output_dir is None:
|
|
output_dir = settings.cache_dir / "models"
|
|
|
|
# Make sure the folder exists
|
|
output_dir.mkdir(exist_ok=True, parents=True)
|
|
|
|
if with_layout:
|
|
_log.info("Downloading layout model...")
|
|
LayoutModel.download_models(
|
|
local_dir=output_dir / LayoutModel._model_repo_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
if with_tableformer:
|
|
_log.info("Downloading tableformer model...")
|
|
TableStructureModel.download_models(
|
|
local_dir=output_dir / TableStructureModel._model_repo_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
if with_picture_classifier:
|
|
_log.info("Downloading picture classifier model...")
|
|
DocumentPictureClassifier.download_models(
|
|
local_dir=output_dir / DocumentPictureClassifier._model_repo_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
if with_code_formula:
|
|
_log.info("Downloading code formula model...")
|
|
CodeFormulaModel.download_models(
|
|
local_dir=output_dir / CodeFormulaModel._model_repo_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
if with_smolvlm:
|
|
_log.info("Downloading SmolVlm model...")
|
|
download_hf_model(
|
|
repo_id=smolvlm_picture_description.repo_id,
|
|
local_dir=output_dir / smolvlm_picture_description.repo_cache_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
if with_smoldocling:
|
|
_log.info("Downloading SmolDocling model...")
|
|
download_hf_model(
|
|
repo_id=SMOLDOCLING_TRANSFORMERS.repo_id,
|
|
local_dir=output_dir / SMOLDOCLING_TRANSFORMERS.repo_cache_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
if with_smoldocling_mlx:
|
|
_log.info("Downloading SmolDocling MLX model...")
|
|
download_hf_model(
|
|
repo_id=SMOLDOCLING_MLX.repo_id,
|
|
local_dir=output_dir / SMOLDOCLING_MLX.repo_cache_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
if with_granite_vision:
|
|
_log.info("Downloading Granite Vision model...")
|
|
download_hf_model(
|
|
repo_id=granite_picture_description.repo_id,
|
|
local_dir=output_dir / granite_picture_description.repo_cache_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
if with_easyocr:
|
|
_log.info("Downloading easyocr models...")
|
|
EasyOcrModel.download_models(
|
|
local_dir=output_dir / EasyOcrModel._model_repo_folder,
|
|
force=force,
|
|
progress=progress,
|
|
)
|
|
|
|
return output_dir
|