metadata
license: apache-2.0
This model provides HuggingFaceTB/SmolVLM-256M-Instruct model in tflite format.
You can use this model with AI Edge Cpp Example.
You need to slightly modify this pipeline to support image as input (see COLAB example below).
Currently, AI Edge Torch vlms not supported
on MediaPipe LLM Inference API,
for example qwen_vl model,
that was used as reference to write SmolVLM-256M-Instruct convertation scripts (coming soon).
Use the models
Colab
Details
The model was converted with:
python convert_to_tflite.py --quantize="dynamic_int8"\
--checkpoint_path='./models/SmolVLM-256M-Instruct' --output_path="./models/SmolVLM-256M-Instruct-tflite"\
--mask_as_input=True --prefill_seq_lens=256 --kv_cache_max_len=2048