TheoMoins commited on
Commit
2e89124
·
verified ·
1 Parent(s): c8c116a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -3
README.md CHANGED
@@ -22,9 +22,6 @@ tags:
22
  MEDUSA is a family of Vision Language Models (VLMs) fine-tuned for **multilingual medieval handwritten text recognition (HTR)** at the **line level**.
23
  These models were developed at the [École nationale des chartes – PSL](https://www.chartes.psl.eu/).
24
 
25
- This repository contains the `0.2` variants of MEDUSA, which extend the [0.1 release](https://huggingface.co/ENC-PSL/Medusa0.1Line-9B) with an explicit
26
- **Silver pre-training stage** on synthetic line images rendered from text-only historical corpora.
27
-
28
  > **Note on versioning.** The `0.1` variants correspond to the models submitted to the ICDAR 2026 competition, trained exclusively on Gold and Platinum image–text pairs.
29
  > The `0.2` variants add a prior Silver stage using 500,000 synthetic lines, improving coverage of under-resourced languages.
30
 
 
22
  MEDUSA is a family of Vision Language Models (VLMs) fine-tuned for **multilingual medieval handwritten text recognition (HTR)** at the **line level**.
23
  These models were developed at the [École nationale des chartes – PSL](https://www.chartes.psl.eu/).
24
 
 
 
 
25
  > **Note on versioning.** The `0.1` variants correspond to the models submitted to the ICDAR 2026 competition, trained exclusively on Gold and Platinum image–text pairs.
26
  > The `0.2` variants add a prior Silver stage using 500,000 synthetic lines, improving coverage of under-resourced languages.
27