Commit
•
1c42c0c
1
Parent(s):
b2bafa7
Push model using huggingface_hub.
Browse files- README.md +93 -89
- model.safetensors +1 -1
- model_head.pkl +1 -1
README.md
CHANGED
|
@@ -8,13 +8,14 @@ tags:
|
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
widget:
|
| 11 |
-
- text:
|
| 12 |
-
employé ?
|
| 13 |
-
- text: Comment déclarer mes impôts et taxes ?
|
| 14 |
-
- text: Quelles sont les règles de tenue de la comptabilité ?
|
| 15 |
-
- text: Quels sont les frais associés à cette procédure ?
|
| 16 |
-
- text: Quelles sont les procédures de recours possibles contre une décision administrative
|
| 17 |
?
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
pipeline_tag: text-classification
|
| 19 |
inference: true
|
| 20 |
base_model: intfloat/multilingual-e5-small
|
|
@@ -30,7 +31,7 @@ model-index:
|
|
| 30 |
split: test
|
| 31 |
metrics:
|
| 32 |
- type: accuracy
|
| 33 |
-
value: 0
|
| 34 |
name: Accuracy
|
| 35 |
---
|
| 36 |
|
|
@@ -62,17 +63,17 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 62 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 63 |
|
| 64 |
### Model Labels
|
| 65 |
-
| Label | Examples
|
| 66 |
-
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
|
| 70 |
## Evaluation
|
| 71 |
|
| 72 |
### Metrics
|
| 73 |
| Label | Accuracy |
|
| 74 |
|:--------|:---------|
|
| 75 |
-
| **all** | 0
|
| 76 |
|
| 77 |
## Uses
|
| 78 |
|
|
@@ -92,7 +93,7 @@ from setfit import SetFitModel
|
|
| 92 |
# Download from the 🤗 Hub
|
| 93 |
model = SetFitModel.from_pretrained("super-cinnamon/fewshot-followup-multi-e5")
|
| 94 |
# Run inference
|
| 95 |
-
preds = model("Comment
|
| 96 |
```
|
| 97 |
|
| 98 |
<!--
|
|
@@ -124,12 +125,12 @@ preds = model("Comment déclarer mes impôts et taxes ?")
|
|
| 124 |
### Training Set Metrics
|
| 125 |
| Training set | Min | Median | Max |
|
| 126 |
|:-------------|:----|:-------|:----|
|
| 127 |
-
| Word count |
|
| 128 |
|
| 129 |
| Label | Training Sample Count |
|
| 130 |
|:------------|:----------------------|
|
| 131 |
-
| independent |
|
| 132 |
-
| follow_up |
|
| 133 |
|
| 134 |
### Training Hyperparameters
|
| 135 |
- batch_size: (8, 8)
|
|
@@ -151,79 +152,82 @@ preds = model("Comment déclarer mes impôts et taxes ?")
|
|
| 151 |
### Training Results
|
| 152 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 153 |
|:------:|:----:|:-------------:|:---------------:|
|
| 154 |
-
| 0.
|
| 155 |
-
| 0.
|
| 156 |
-
| 0.
|
| 157 |
-
| 0.
|
| 158 |
-
| 0.
|
| 159 |
-
| 0.
|
| 160 |
-
| 0.
|
| 161 |
-
| 0.
|
| 162 |
-
| 1.
|
| 163 |
-
| 1.
|
| 164 |
-
| 1.
|
| 165 |
-
| 1.
|
| 166 |
-
| 1.
|
| 167 |
-
| 1.
|
| 168 |
-
| 1.
|
| 169 |
-
|
|
| 170 |
-
| 2.
|
| 171 |
-
| 2.
|
| 172 |
-
| 2.
|
| 173 |
-
| 2.
|
| 174 |
-
| 2.
|
| 175 |
-
| 2.
|
| 176 |
-
|
|
| 177 |
-
| 3.
|
| 178 |
-
| 3.
|
| 179 |
-
| 3.
|
| 180 |
-
| 3.
|
| 181 |
-
| 3.
|
| 182 |
-
| 3.
|
| 183 |
-
|
|
| 184 |
-
|
|
| 185 |
-
| 4.
|
| 186 |
-
| 4.
|
| 187 |
-
| 4.
|
| 188 |
-
| 4.
|
| 189 |
-
| 4.
|
| 190 |
-
| 4.
|
| 191 |
-
|
|
| 192 |
-
| 5.
|
| 193 |
-
| 5.
|
| 194 |
-
| 5.
|
| 195 |
-
| 5.
|
| 196 |
-
| 5.
|
| 197 |
-
| 5.
|
| 198 |
-
|
|
| 199 |
-
|
|
| 200 |
-
| 6.
|
| 201 |
-
| 6.
|
| 202 |
-
| 6.
|
| 203 |
-
| 6.
|
| 204 |
-
| 6.
|
| 205 |
-
|
|
| 206 |
-
|
|
| 207 |
-
| 7.
|
| 208 |
-
| 7.
|
| 209 |
-
| 7.
|
| 210 |
-
| 7.
|
| 211 |
-
| 7.
|
| 212 |
-
|
|
| 213 |
-
|
|
| 214 |
-
|
|
| 215 |
-
| 8.
|
| 216 |
-
| 8.
|
| 217 |
-
| 8.
|
| 218 |
-
| 8.
|
| 219 |
-
| 8.
|
| 220 |
-
|
|
| 221 |
-
|
|
| 222 |
-
| 9.
|
| 223 |
-
| 9.
|
| 224 |
-
| 9.
|
| 225 |
-
| 9.
|
| 226 |
-
| 9.
|
|
|
|
|
|
|
|
|
|
| 227 |
|
| 228 |
### Framework Versions
|
| 229 |
- Python: 3.10.12
|
|
|
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
widget:
|
| 11 |
+
- text: Quelles sont les règles en matière de garde d'enfants et de pension alimentaire
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
?
|
| 13 |
+
- text: Comment se déroule une procédure de divorce ?
|
| 14 |
+
- text: Quelles sont les principales difficultés rencontrées dans l'application de
|
| 15 |
+
cette loi ?
|
| 16 |
+
- text: Quels sont les régimes matrimoniaux possibles ?
|
| 17 |
+
- text: Comment peut-on obtenir réparation pour un préjudice subi du fait d'une décision
|
| 18 |
+
administrative illégale ?
|
| 19 |
pipeline_tag: text-classification
|
| 20 |
inference: true
|
| 21 |
base_model: intfloat/multilingual-e5-small
|
|
|
|
| 31 |
split: test
|
| 32 |
metrics:
|
| 33 |
- type: accuracy
|
| 34 |
+
value: 1.0
|
| 35 |
name: Accuracy
|
| 36 |
---
|
| 37 |
|
|
|
|
| 63 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 64 |
|
| 65 |
### Model Labels
|
| 66 |
+
| Label | Examples |
|
| 67 |
+
|:------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 68 |
+
| independent | <ul><li>'Comment rédiger un contrat de travail ?'</li><li>'Quels sont les impôts et taxes applicables aux entreprises ?'</li><li>'Comment peut-on contester un licenciement abusif ?'</li></ul> |
|
| 69 |
+
| follow_up | <ul><li>'Quelles sont les conséquences de cette loi ?'</li><li>"Comment cette loi s'inscrit-elle dans le cadre plus large du droit algérien ?"</li><li>"Comment puis-je obtenir plus d'informations sur ce sujet ?"</li></ul> |
|
| 70 |
|
| 71 |
## Evaluation
|
| 72 |
|
| 73 |
### Metrics
|
| 74 |
| Label | Accuracy |
|
| 75 |
|:--------|:---------|
|
| 76 |
+
| **all** | 1.0 |
|
| 77 |
|
| 78 |
## Uses
|
| 79 |
|
|
|
|
| 93 |
# Download from the 🤗 Hub
|
| 94 |
model = SetFitModel.from_pretrained("super-cinnamon/fewshot-followup-multi-e5")
|
| 95 |
# Run inference
|
| 96 |
+
preds = model("Comment se déroule une procédure de divorce ?")
|
| 97 |
```
|
| 98 |
|
| 99 |
<!--
|
|
|
|
| 125 |
### Training Set Metrics
|
| 126 |
| Training set | Min | Median | Max |
|
| 127 |
|:-------------|:----|:-------|:----|
|
| 128 |
+
| Word count | 1 | 9.6184 | 16 |
|
| 129 |
|
| 130 |
| Label | Training Sample Count |
|
| 131 |
|:------------|:----------------------|
|
| 132 |
+
| independent | 43 |
|
| 133 |
+
| follow_up | 33 |
|
| 134 |
|
| 135 |
### Training Hyperparameters
|
| 136 |
- batch_size: (8, 8)
|
|
|
|
| 152 |
### Training Results
|
| 153 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 154 |
|:------:|:----:|:-------------:|:---------------:|
|
| 155 |
+
| 0.0027 | 1 | 0.3915 | - |
|
| 156 |
+
| 0.1326 | 50 | 0.3193 | - |
|
| 157 |
+
| 0.2653 | 100 | 0.2252 | - |
|
| 158 |
+
| 0.3979 | 150 | 0.1141 | - |
|
| 159 |
+
| 0.5305 | 200 | 0.0197 | - |
|
| 160 |
+
| 0.6631 | 250 | 0.0019 | - |
|
| 161 |
+
| 0.7958 | 300 | 0.0021 | - |
|
| 162 |
+
| 0.9284 | 350 | 0.0002 | - |
|
| 163 |
+
| 1.0610 | 400 | 0.0008 | - |
|
| 164 |
+
| 1.1936 | 450 | 0.0005 | - |
|
| 165 |
+
| 1.3263 | 500 | 0.0002 | - |
|
| 166 |
+
| 1.4589 | 550 | 0.0002 | - |
|
| 167 |
+
| 1.5915 | 600 | 0.0007 | - |
|
| 168 |
+
| 1.7241 | 650 | 0.0001 | - |
|
| 169 |
+
| 1.8568 | 700 | 0.0003 | - |
|
| 170 |
+
| 1.9894 | 750 | 0.0002 | - |
|
| 171 |
+
| 2.1220 | 800 | 0.0001 | - |
|
| 172 |
+
| 2.2546 | 850 | 0.0002 | - |
|
| 173 |
+
| 2.3873 | 900 | 0.0 | - |
|
| 174 |
+
| 2.5199 | 950 | 0.0003 | - |
|
| 175 |
+
| 2.6525 | 1000 | 0.0001 | - |
|
| 176 |
+
| 2.7851 | 1050 | 0.0001 | - |
|
| 177 |
+
| 2.9178 | 1100 | 0.0001 | - |
|
| 178 |
+
| 3.0504 | 1150 | 0.0001 | - |
|
| 179 |
+
| 3.1830 | 1200 | 0.0001 | - |
|
| 180 |
+
| 3.3156 | 1250 | 0.0001 | - |
|
| 181 |
+
| 3.4483 | 1300 | 0.0001 | - |
|
| 182 |
+
| 3.5809 | 1350 | 0.0001 | - |
|
| 183 |
+
| 3.7135 | 1400 | 0.0 | - |
|
| 184 |
+
| 3.8462 | 1450 | 0.0 | - |
|
| 185 |
+
| 3.9788 | 1500 | 0.0 | - |
|
| 186 |
+
| 4.1114 | 1550 | 0.0 | - |
|
| 187 |
+
| 4.2440 | 1600 | 0.0001 | - |
|
| 188 |
+
| 4.3767 | 1650 | 0.0001 | - |
|
| 189 |
+
| 4.5093 | 1700 | 0.0001 | - |
|
| 190 |
+
| 4.6419 | 1750 | 0.0001 | - |
|
| 191 |
+
| 4.7745 | 1800 | 0.0 | - |
|
| 192 |
+
| 4.9072 | 1850 | 0.0001 | - |
|
| 193 |
+
| 5.0398 | 1900 | 0.0 | - |
|
| 194 |
+
| 5.1724 | 1950 | 0.0001 | - |
|
| 195 |
+
| 5.3050 | 2000 | 0.0 | - |
|
| 196 |
+
| 5.4377 | 2050 | 0.0001 | - |
|
| 197 |
+
| 5.5703 | 2100 | 0.0 | - |
|
| 198 |
+
| 5.7029 | 2150 | 0.0 | - |
|
| 199 |
+
| 5.8355 | 2200 | 0.0 | - |
|
| 200 |
+
| 5.9682 | 2250 | 0.0001 | - |
|
| 201 |
+
| 6.1008 | 2300 | 0.0001 | - |
|
| 202 |
+
| 6.2334 | 2350 | 0.0 | - |
|
| 203 |
+
| 6.3660 | 2400 | 0.0001 | - |
|
| 204 |
+
| 6.4987 | 2450 | 0.0 | - |
|
| 205 |
+
| 6.6313 | 2500 | 0.0 | - |
|
| 206 |
+
| 6.7639 | 2550 | 0.0 | - |
|
| 207 |
+
| 6.8966 | 2600 | 0.0 | - |
|
| 208 |
+
| 7.0292 | 2650 | 0.0 | - |
|
| 209 |
+
| 7.1618 | 2700 | 0.0 | - |
|
| 210 |
+
| 7.2944 | 2750 | 0.0 | - |
|
| 211 |
+
| 7.4271 | 2800 | 0.0001 | - |
|
| 212 |
+
| 7.5597 | 2850 | 0.0 | - |
|
| 213 |
+
| 7.6923 | 2900 | 0.0 | - |
|
| 214 |
+
| 7.8249 | 2950 | 0.0 | - |
|
| 215 |
+
| 7.9576 | 3000 | 0.0 | - |
|
| 216 |
+
| 8.0902 | 3050 | 0.0 | - |
|
| 217 |
+
| 8.2228 | 3100 | 0.0 | - |
|
| 218 |
+
| 8.3554 | 3150 | 0.0 | - |
|
| 219 |
+
| 8.4881 | 3200 | 0.0001 | - |
|
| 220 |
+
| 8.6207 | 3250 | 0.0 | - |
|
| 221 |
+
| 8.7533 | 3300 | 0.0 | - |
|
| 222 |
+
| 8.8859 | 3350 | 0.0 | - |
|
| 223 |
+
| 9.0186 | 3400 | 0.0001 | - |
|
| 224 |
+
| 9.1512 | 3450 | 0.0 | - |
|
| 225 |
+
| 9.2838 | 3500 | 0.0 | - |
|
| 226 |
+
| 9.4164 | 3550 | 0.0001 | - |
|
| 227 |
+
| 9.5491 | 3600 | 0.0 | - |
|
| 228 |
+
| 9.6817 | 3650 | 0.0001 | - |
|
| 229 |
+
| 9.8143 | 3700 | 0.0 | - |
|
| 230 |
+
| 9.9469 | 3750 | 0.0001 | - |
|
| 231 |
|
| 232 |
### Framework Versions
|
| 233 |
- Python: 3.10.12
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 470637416
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0e9b68689e31d9dd26cd0ae229f8b0e9a77175dd7d05f0aa926f3ca9e8b3982
|
| 3 |
size 470637416
|
model_head.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3919
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8025980af9860194e78809812a5d8cbbf3732633501a97b105bca3de852e4926
|
| 3 |
size 3919
|