[smolvlm] make CI green (#36306)

* add smolvlm to toctree

* add requirements

* dev-ci

* no docker changes

* dev-ci

* update torch-light.dockerfile

* derp

* dev-ci

docker/tf-light.dockerfile

@@ -7,6 +7,6 @@ RUN apt-get install -y  cmake
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv venv && uv pip install --no-cache-dir -U pip setuptools
 RUN pip install  --upgrade --no-cache-dir "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[tf-cpu,sklearn,testing,sentencepiece,tf-speech,vision]"
-RUN uv pip install --no-cache-dir  "protobuf==3.20.3" 
+RUN uv pip install --no-cache-dir  "protobuf==3.20.3"
 RUN pip uninstall -y transformers
-RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean
+RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean

docker/torch-light.dockerfile

@@ -7,5 +7,5 @@ ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv venv && uv pip install --no-cache-dir -U pip setuptools
 RUN pip install --no-cache-dir 'torch' 'torchvision' 'torchaudio' --index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-deps timm accelerate --extra-index-url https://download.pytorch.org/whl/cpu
-RUN uv pip install --no-cache-dir librosa "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[sklearn,sentencepiece,vision,testing,tiktoken]"
+RUN uv pip install --no-cache-dir librosa "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[sklearn,sentencepiece,vision,testing,tiktoken,num2words]"
-RUN pip uninstall -y transformers
+RUN pip uninstall -y transformers

docs/source/en/_toctree.yml

@@ -965,6 +965,8 @@
         title: Segment Anything
       - local: model_doc/siglip
         title: SigLIP
+      - local: model_doc/smolvlm
+        title: SmolVLM
       - local: model_doc/speech-encoder-decoder
         title: Speech Encoder Decoder Models
       - local: model_doc/tapas

setup.py

@@ -130,8 +130,9 @@ _deps = [
     "keras>2.9,<2.16",
     "keras-nlp>=0.3.1,<0.14.0",  # keras-nlp 0.14 doesn't support keras 2, see pin on keras.
     "librosa",
-    "nltk<=3.8.1",
     "natten>=0.14.6,<0.15.0",
+    "nltk<=3.8.1",
+    "num2words",
     "numpy>=1.17",
     "onnxconverter-common",
     "onnxruntime-tools>=1.4.2",
@@ -314,7 +315,7 @@ extras["torch-vision"] = deps_list("torchvision") + extras["vision"]
 extras["natten"] = deps_list("natten")
 extras["codecarbon"] = deps_list("codecarbon")
 extras["video"] = deps_list("av")
-
+extras["num2words"] = deps_list("num2words")
 extras["sentencepiece"] = deps_list("sentencepiece", "protobuf")
 extras["tiktoken"] = deps_list("tiktoken", "blobfile")
 extras["testing"] = (
@@ -364,6 +365,7 @@ extras["all"] = (
     + extras["codecarbon"]
     + extras["accelerate"]
     + extras["video"]
+    + extras["num2words"]
 )
 
 
@@ -383,6 +385,7 @@ extras["dev-torch"] = (
     + extras["sklearn"]
     + extras["modelcreation"]
     + extras["onnxruntime"]
+    + extras["num2words"]
 )
 extras["dev-tensorflow"] = (
     extras["testing"]

src/transformers/dependency_versions_table.py

@@ -36,8 +36,9 @@ deps = {
     "keras": "keras>2.9,<2.16",
     "keras-nlp": "keras-nlp>=0.3.1,<0.14.0",
     "librosa": "librosa",
-    "nltk": "nltk<=3.8.1",
     "natten": "natten>=0.14.6,<0.15.0",
+    "nltk": "nltk<=3.8.1",
+    "num2words": "num2words",
     "numpy": "numpy>=1.17",
     "onnxconverter-common": "onnxconverter-common",
     "onnxruntime-tools": "onnxruntime-tools>=1.4.2",