Visual Document Retrieval
ColPali
coreai
coreai-aimodel
core-ai
apple
on-device
late-interaction
colbert
retrieval
Instructions to use mlboydaisuke/ColModernVBERT-CoreAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ColPali
How to use mlboydaisuke/ColModernVBERT-CoreAI with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure)
Browse files
doc/colmodernvbert-doc_float16_s89_static.aimodel/main.hash
CHANGED
|
Binary files a/doc/colmodernvbert-doc_float16_s89_static.aimodel/main.hash and b/doc/colmodernvbert-doc_float16_s89_static.aimodel/main.hash differ
|
|
|
doc/colmodernvbert-doc_float16_s89_static.aimodel/main.mlirb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b71e2713dbb23cf281fed0c8a5d273da44236b85f5ae0bf3b605f18009ba03d
|
| 3 |
+
size 426938382
|
doc/colmodernvbert-doc_float16_s89_static.aimodel/metadata.json
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"description" : "ColModernVBERT visual document retriever (document\/image encoder, single 512px tile): SigLIP2 vision + pixel-shuffle x4 -> ModernBERT-150M -> custom_text_proj(768->128) -> per-token L2-normalized 128-d multi-vector for ColBERT-style late-interaction (MaxSim). https:\/\/huggingface.co\/ModernVBERT\/colmodernvbert",
|
| 3 |
-
"
|
| 4 |
-
"license" : "MIT",
|
| 5 |
"assetVersion" : "2.0",
|
| 6 |
-
"
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"author" : "ModernVBERT (Illuin Technology \/ ETH)",
|
| 3 |
"description" : "ColModernVBERT visual document retriever (document\/image encoder, single 512px tile): SigLIP2 vision + pixel-shuffle x4 -> ModernBERT-150M -> custom_text_proj(768->128) -> per-token L2-normalized 128-d multi-vector for ColBERT-style late-interaction (MaxSim). https:\/\/huggingface.co\/ModernVBERT\/colmodernvbert",
|
| 4 |
+
"producer" : "coreai-core 1.0.0b2",
|
|
|
|
| 5 |
"assetVersion" : "2.0",
|
| 6 |
+
"creationDate" : "20260720T163245Z",
|
| 7 |
+
"license" : "MIT"
|
| 8 |
}
|