Update README.md
Browse files
README.md
CHANGED
|
@@ -2,20 +2,26 @@
|
|
| 2 |
name: apple-fastvlm-vision-projector-512
|
| 3 |
model_file: vision_projector_v1_standalone.onnx
|
| 4 |
license: mit
|
| 5 |
-
language:
|
|
|
|
| 6 |
framework: onnx
|
| 7 |
pipeline_tag: feature-extraction
|
| 8 |
tags:
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
description:
|
| 18 |
-
A standalone ONNX vision projector extracted from the FastVLM pipeline.
|
| 19 |
-
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
---
|
|
|
|
| 2 |
name: apple-fastvlm-vision-projector-512
|
| 3 |
model_file: vision_projector_v1_standalone.onnx
|
| 4 |
license: mit
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
framework: onnx
|
| 8 |
pipeline_tag: feature-extraction
|
| 9 |
tags:
|
| 10 |
+
- fastvlm 0.5B
|
| 11 |
+
- apple's fast vlm
|
| 12 |
+
- onnx
|
| 13 |
+
- vision
|
| 14 |
+
- image-encoder
|
| 15 |
+
- multimodal
|
| 16 |
+
- fastvlm
|
| 17 |
+
- cpu
|
| 18 |
+
description: >
|
| 19 |
+
A standalone ONNX vision projector extracted from the FastVLM pipeline.
|
| 20 |
+
Converts image features into the FastVLM multimodal embedding space and is
|
| 21 |
+
designed for CPU-based image-to-text and vision+language inference.
|
| 22 |
+
usage: >
|
| 23 |
+
Use this model to convert images into embeddings for a compatible FastVLM
|
| 24 |
+
language backbone.
|
| 25 |
+
base_model:
|
| 26 |
+
- apple/FastVLM-0.5B
|
| 27 |
---
|