Distilvit ONNX
This is an ONNX version of Mozilla/distilvit. It was automatically converted and uploaded using this Hugging Face Space.
Model source
- Kind
- Other
- File size
- 47.4–367 MB
- Base model
- Mozilla/distilvit
- Version
- vRevision 4853325
- Updated
- Sep 17, 2026
- Downloads
- 17
- Tasks
- Captioning
- Source
- Hugging Face
Source description
distilvit (ONNX)
This is an ONNX version of Mozilla/distilvit. It was automatically converted and uploaded using this Hugging Face Space.
Usage with Transformers.js
See the pipeline documentation for image-to-text: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.ImageToTextPipeline
distilvit
This model is a work in progress. Fine-tuned version of those base models:
- a VIT model for the image encoder: https://huggingface.co/google/vit-base-patch16-224-in21k
- a Distilled GPT-2 model for the text decoder: https://huggingface.co/distilbert/distilgpt2
This model was trained on:
- A debiased version of COCO 2017
- A debiased version of Flickr30k
- Images from pexels
- DocOrNot
- Alt Text Validation
You can find the code used to create the model here: https://github.com/mozilla/distilvit
training results
{
"train/loss": 0.0781,
"train/learning_rate": 0.00003793103448275862,
"train/epoch": 2.41,
"train/global_step": 700,
"eval/loss": 0.09741172194480896,
"eval/rouge1": 60.382,
"eval/rouge2": 38.0754,
"eval/rougeL": 56.9132,
"eval/rougeLsum": 56.9214,
"eval/meteor": 0.5448683804505693,
"eval/gen_len": 9.864678265672467,
"eval/runtime": 343.0443,
"eval/samples_per_second": 10.555,
"eval/steps_per_second": 0.108,
"train/train_runtime": 10567.9413,
"train/train_samples_per_second": 27.414,
"train/train_steps_per_second": 0.274,
"train/total_flos": 9039628706135409000,
"train/train_loss": 0.09852950266429356,
}
Sources
1 source
Sources
1 sourceVerified Sep 17
Model artifacts
32 artifacts
Model artifacts
32 artifactsonnx/decoder_model_merged_q4f16.onnx
onnx · 184 MB · SHA-256 4a9db461eac3…e253 · Hugging Face
Downloadonnx/decoder_model_merged_quantized.onnx
onnx · 240 MB · SHA-256 d56f4b23dea8…508c · Hugging Face
Downloadonnx/decoder_model_merged_uint8.onnx
onnx · 240 MB · SHA-256 f83d25a2caeb…32ac · Hugging Face
Downloadonnx/decoder_with_past_model_bnb4.onnx
onnx · 367 MB · SHA-256 3f47d55834b1…2428 · Hugging Face
Downloadonnx/decoder_with_past_model_fp16.onnx
onnx · 183 MB · SHA-256 83f95d839e10…4449 · Hugging Face
Downloadonnx/decoder_with_past_model_int8.onnx
onnx · 239 MB · SHA-256 e5587b8027c7…a66b · Hugging Face
Downloadonnx/decoder_with_past_model_q4.onnx
onnx · 367 MB · SHA-256 3f47d55834b1…2428 · Hugging Face
Downloadonnx/decoder_with_past_model_q4f16.onnx
onnx · 183 MB · SHA-256 b3e271cce8cc…1203 · Hugging Face
Downloadonnx/decoder_with_past_model_quantized.onnx
onnx · 239 MB · SHA-256 e5587b8027c7…a66b · Hugging Face
Downloadonnx/decoder_with_past_model_uint8.onnx
onnx · 239 MB · SHA-256 054773061933…a2f7 · Hugging Face
DownloadSource excerpts
2 excerpts
Source excerpts
2 excerpts--- tags: - image-to-text - image-captioning - transformers.js license: apache-2.0 metrics: - rouge datasets: - Mozilla/flickr30k-transformed-captions-gpt4o widget: - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg example_title: Savanna - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg example_title: Football Match - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg example_title: Airport base_model: - Mozilla/distilvit library_name: transformers.js pipeline_tag: image-to-text --- # distilvit (ONNX) This is an ONNX version of [Mozilla/distilvit](https://huggingface.co/Mozilla/distilvit). It was automatically converted and uploaded using [this Hugging Face Space](https://huggingface.co/spaces/onnx-community/convert-to-onnx). ## Usage with Transformers.js See the pipeline documentation for `image-to-text`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.ImageToTextPipeline --- # distilvit This model is a work in progress. Fine-tuned version of those base models: - a VIT model for the image encoder: https://huggingface.co/google/vit-base-patch16-224-in21k - a Distilled GPT-2 model for the text decoder: https://huggingface.co/distilbert/distilgpt2 This model was trained on: - [A debiased version of COCO 2017](https://huggingface.co/datasets/Mozilla/coco-gpt4o) - [A debiased version of Flickr30k](https://huggingface.co/datasets/Mozilla/flickr30k-transformed-captions-gpt4o) - [Images from pexels](https://huggingface.co/datasets/Mozilla/pexels-gpt4o) - [DocOrNot](https://huggingface.co/datasets/Mozilla/docornot) - [Alt Text Validation](https://huggingface.co/datasets/Mozilla/alt-text-validation) You can find the code used to create the model here: https://github.com/mozilla/distilvit # training results ``` { "train/loss": 0.0781, "train/learning_rate": 0.00003793103448275862, "train/epoch": 2.41, "train/global_step": 700, "eval/loss": 0.09741172194480896, "eval/rouge1": 60.382, "eval/rouge2": 38.0754, "eval/rougeL": 56.9132, "eval/rougeLsum": 56.9214, "eval/meteor": 0.5448683804505693, "eval/gen_len": 9.864678265672467, "eval/runtime": 343.0443, "eval/samples_per_second": 10.555, "eval/steps_per_second": 0.108, "train/train_runtime": 10567.9413, "train/train_samples_per_second": 27.414, "train/...
Source context: 17 downloads · 0 likes · Pipeline image-to-text · Library transformers.js · Repo onnx-community/distilvit-ONNX
