Update README.md
Browse files
README.md
CHANGED
@@ -11,7 +11,7 @@ tags:
|
|
11 |
- pytorch
|
12 |
---
|
13 |
|
14 |
-
# Jargon-general-
|
15 |
|
16 |
[Jargon](https://hal.science/hal-04535557/file/FB2_domaines_specialises_LREC_COLING24.pdf) is an efficient transformer encoder LM for French, combining the LinFormer attention mechanism with the RoBERTa model architecture.
|
17 |
|
@@ -24,20 +24,24 @@ Jargon is available in several versions with different context sizes and types o
|
|
24 |
|
25 |
|
26 |
|
|
|
27 |
## Using Jargon models with HuggingFace transformers
|
28 |
|
29 |
-
You can get started with `jargon-general-
|
30 |
|
31 |
```python
|
32 |
from transformers import AutoModelForMaskedLM, AutoTokenizer, pipeline
|
33 |
|
34 |
-
tokenizer = AutoTokenizer.from_pretrained("PantagrueLLM/jargon-general-
|
35 |
-
model = AutoModelForMaskedLM.from_pretrained("PantagrueLLM/jargon-general-
|
36 |
|
37 |
jargon_maskfiller = pipeline("fill-mask", model=model, tokenizer=tokenizer)
|
38 |
output = jargon_maskfiller("Il est allé au <mask> hier")
|
39 |
```
|
40 |
|
|
|
|
|
|
|
41 |
- **Funded by**
|
42 |
- GENCI-IDRIS (Grant 2022 A0131013801)
|
43 |
- French National Research Agency: Pantagruel grant ANR-23-IAS1-0001
|
@@ -50,8 +54,38 @@ output = jargon_maskfiller("Il est allé au <mask> hier")
|
|
50 |
- **Language(s):** French
|
51 |
- **License:** MIT
|
52 |
- **Developed by:** Vincent Segonne
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
<!-- - **Finetuned from model [optional]:** [More Information Needed] -->
|
54 |
<!--
|
55 |
### Model Sources [optional]
|
56 |
|
|
|
57 |
<!-- Provide the basic links for the model. -->
|
|
|
11 |
- pytorch
|
12 |
---
|
13 |
|
14 |
+
# Jargon-general-biomed
|
15 |
|
16 |
[Jargon](https://hal.science/hal-04535557/file/FB2_domaines_specialises_LREC_COLING24.pdf) is an efficient transformer encoder LM for French, combining the LinFormer attention mechanism with the RoBERTa model architecture.
|
17 |
|
|
|
24 |
|
25 |
|
26 |
|
27 |
+
|
28 |
## Using Jargon models with HuggingFace transformers
|
29 |
|
30 |
+
You can get started with `jargon-general-biomed` using the code snippet below:
|
31 |
|
32 |
```python
|
33 |
from transformers import AutoModelForMaskedLM, AutoTokenizer, pipeline
|
34 |
|
35 |
+
tokenizer = AutoTokenizer.from_pretrained("PantagrueLLM/jargon-general-biomed", trust_remote_code=True)
|
36 |
+
model = AutoModelForMaskedLM.from_pretrained("PantagrueLLM/jargon-general-biomed", trust_remote_code=True)
|
37 |
|
38 |
jargon_maskfiller = pipeline("fill-mask", model=model, tokenizer=tokenizer)
|
39 |
output = jargon_maskfiller("Il est allé au <mask> hier")
|
40 |
```
|
41 |
|
42 |
+
You can also use the classes `AutoModel`, `AutoModelForSequenceClassification`, or `AutoModelForTokenClassification` to load Jargon models, depending on the downstream task in question.
|
43 |
+
|
44 |
+
|
45 |
- **Funded by**
|
46 |
- GENCI-IDRIS (Grant 2022 A0131013801)
|
47 |
- French National Research Agency: Pantagruel grant ANR-23-IAS1-0001
|
|
|
54 |
- **Language(s):** French
|
55 |
- **License:** MIT
|
56 |
- **Developed by:** Vincent Segonne
|
57 |
+
|
58 |
+
|
59 |
+
|
60 |
+
## Citation
|
61 |
+
|
62 |
+
If you use this model for your own research work, please cite as follows:
|
63 |
+
|
64 |
+
```bibtex
|
65 |
+
@inproceedings{segonne:hal-04535557,
|
66 |
+
TITLE = {{Jargon: A Suite of Language Models and Evaluation Tasks for French Specialized Domains}},
|
67 |
+
AUTHOR = {Segonne, Vincent and Mannion, Aidan and Alonzo Canul, Laura Cristina and Audibert, Alexandre and Liu, Xingyu and Macaire, C{\'e}cile and Pupier, Adrien and Zhou, Yongxin and Aguiar, Mathilde and Herron, Felix and Norr{\'e}, Magali and Amini, Massih-Reza and Bouillon, Pierrette and Eshkol-Taravella, Iris and Esperan{\c c}a-Rodier, Emmanuelle and Fran{\c c}ois, Thomas and Goeuriot, Lorraine and Goulian, J{\'e}r{\^o}me and Lafourcade, Mathieu and Lecouteux, Benjamin and Portet, Fran{\c c}ois and Ringeval, Fabien and Vandeghinste, Vincent and Coavoux, Maximin and Dinarelli, Marco and Schwab, Didier},
|
68 |
+
URL = {https://hal.science/hal-04535557},
|
69 |
+
BOOKTITLE = {{LREC-COLING 2024 - Joint International Conference on Computational Linguistics, Language Resources and Evaluation}},
|
70 |
+
ADDRESS = {Turin, Italy},
|
71 |
+
YEAR = {2024},
|
72 |
+
MONTH = May,
|
73 |
+
KEYWORDS = {Self-supervised learning ; Pretrained language models ; Evaluation benchmark ; Biomedical document processing ; Legal document processing ; Speech transcription},
|
74 |
+
PDF = {https://hal.science/hal-04535557/file/FB2_domaines_specialises_LREC_COLING24.pdf},
|
75 |
+
HAL_ID = {hal-04535557},
|
76 |
+
HAL_VERSION = {v1},
|
77 |
+
}
|
78 |
+
```
|
79 |
+
|
80 |
+
|
81 |
+
|
82 |
+
|
83 |
+
|
84 |
+
|
85 |
+
|
86 |
<!-- - **Finetuned from model [optional]:** [More Information Needed] -->
|
87 |
<!--
|
88 |
### Model Sources [optional]
|
89 |
|
90 |
+
|
91 |
<!-- Provide the basic links for the model. -->
|