Hugging Face's logo

PantagrueLLM
/
text-base-croissant-mlm-old

Feature Extraction
Transformers
Safetensors
Fairseq
French
pantagruel_uni
data2vec2
JEPA
text
custom_code
Model card Files
xet
 Community
vpelloin commited on
Commit
b67eab0
·
verified ·
1 Parent(s): 4012e22

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -7
README.md CHANGED
@@ -5,7 +5,12 @@ datasets:
5
  language:
6
  - fr
7
  pipeline_tag: feature-extraction
8
- library_name: fairseq
 
 
 
 
 
9
  ---
10
 
11
  # Pantagruel: Unified Self-Supervised Encoders for French Text and Speech
@@ -31,13 +36,13 @@ Pantagruel text encoders are trained on large-scale French text corpora, includi
31
 
32
  The table below presents the accuracy of the natural language inference task on the French XNLI dataset.
33
 
34
- | **HuggingFace name**| **Model name (paper)** | **Arch/ Params** | **Pretrained dataset** | **Accuracy on XNLI (FR) (dev / test)** |
35
  |----------|------------------------|-----------------|----------------------|---------------------------------------|
36
- | text-base-camtok-wiki | Pantagruel-B-camtok-Wk | Base / 110M | French Wikipedia 2019 (4GB) | 76.94% / 77.43% |
37
- | text-base-wiki | Pantagruel-B-Wk | Base / 125M | French Wikipedia 2019 (4GB) | 77.40% / 78.41% |
38
- | text-base-wiki-mlm | Pantagruel-B-Wk-MLM | Base / 125M | French Wikipedia 2019 (4GB) | 78.25% / 78.41% |
39
- | text-base-camtok-oscar | Pantagruel-B-camtok-Osc | Base / 110M | OSCAR 2019 (138GB) | 80.40% / 80.53% |
40
- | text-base-oscar-mlm | Pantagruel-B-Osc-MLM | Base / 125M | OSCAR 2019 (138GB) | 81.11% / 81.52% |
41
  | text-base-croissant-mlm | Pantagruel-B-Crs-MLM | Base / 125M | croissantLLM (1.5GB) | 81.05% / 80.69% |
42
 
43
  For more downstream tasks and evaluation datasets, please refer to [our paper](https://arxiv.org/abs/2601.05911).
 
5
  language:
6
  - fr
7
  pipeline_tag: feature-extraction
8
+ library_name: transformers
9
+ tags:
10
+ - data2vec2
11
+ - JEPA
12
+ - text
13
+ - fairseq
14
  ---
15
 
16
  # Pantagruel: Unified Self-Supervised Encoders for French Text and Speech
 
36
 
37
  The table below presents the accuracy of the natural language inference task on the French XNLI dataset.
38
 
39
+ | **HuggingFace name**| **Model name (paper)** | **Arch/ Params** | **Pretrained dataset** | **Accuracy on XNLI (FR) (dev / test)** |
40
  |----------|------------------------|-----------------|----------------------|---------------------------------------|
41
+ | [text-base-camtok-wiki](https://huggingface.co/PantagrueLLM/text-base-camtok-wiki) | Pantagruel-B-camtok-Wk | Base / 110M | French Wikipedia 2019 (4GB) | 76.94% / 77.43% |
42
+ | [text-base-wiki](https://huggingface.co/PantagrueLLM/text-base-wiki) | Pantagruel-B-Wk | Base / 125M | French Wikipedia 2019 (4GB) | 77.40% / 78.41% |
43
+ | [text-base-wiki-mlm](https://huggingface.co/PantagrueLLM/text-base-wiki-mlm) | Pantagruel-B-Wk-MLM | Base / 125M | French Wikipedia 2019 (4GB) | 78.25% / 78.41% |
44
+ | [text-base-camtok-oscar](https://huggingface.co/PantagrueLLM/text-base-camtok-oscar) | Pantagruel-B-camtok-Osc | Base / 110M | OSCAR 2019 (138GB) | 80.40% / 80.53% |
45
+ | [text-base-oscar-mlm](https://huggingface.co/PantagrueLLM/text-base-oscar-mlm) | Pantagruel-B-Osc-MLM | Base / 125M | OSCAR 2019 (138GB) | 81.11% / 81.52% |
46
  | text-base-croissant-mlm | Pantagruel-B-Crs-MLM | Base / 125M | croissantLLM (1.5GB) | 81.05% / 80.69% |
47
 
48
  For more downstream tasks and evaluation datasets, please refer to [our paper](https://arxiv.org/abs/2601.05911).