Push model using huggingface_hub.
Browse files- README.md +81 -79
- config_sentence_transformers.json +2 -2
- config_setfit.json +2 -2
- model.safetensors +1 -1
- model_head.pkl +1 -1
README.md
CHANGED
|
@@ -10,12 +10,14 @@ tags:
|
|
| 10 |
- text-classification
|
| 11 |
- generated_from_setfit_trainer
|
| 12 |
widget:
|
| 13 |
-
- text:
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
- text:
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
| 19 |
inference: true
|
| 20 |
model-index:
|
| 21 |
- name: SetFit with akhooli/sbert_ar_nli_500k_ubc_norm
|
|
@@ -29,7 +31,7 @@ model-index:
|
|
| 29 |
split: test
|
| 30 |
metrics:
|
| 31 |
- type: accuracy
|
| 32 |
-
value: 0.
|
| 33 |
name: Accuracy
|
| 34 |
---
|
| 35 |
|
|
@@ -61,17 +63,17 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 61 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 62 |
|
| 63 |
### Model Labels
|
| 64 |
-
| Label | Examples
|
| 65 |
-
|:---------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
|
| 69 |
## Evaluation
|
| 70 |
|
| 71 |
### Metrics
|
| 72 |
| Label | Accuracy |
|
| 73 |
|:--------|:---------|
|
| 74 |
-
| **all** | 0.
|
| 75 |
|
| 76 |
## Uses
|
| 77 |
|
|
@@ -91,7 +93,7 @@ from setfit import SetFitModel
|
|
| 91 |
# Download from the 🤗 Hub
|
| 92 |
model = SetFitModel.from_pretrained("akhooli/setfit_ar_ubc_hs")
|
| 93 |
# Run inference
|
| 94 |
-
preds = model("
|
| 95 |
```
|
| 96 |
|
| 97 |
<!--
|
|
@@ -123,12 +125,12 @@ preds = model("التشكيك بصدق باسيل التشكيك بصدق الس
|
|
| 123 |
### Training Set Metrics
|
| 124 |
| Training set | Min | Median | Max |
|
| 125 |
|:-------------|:----|:--------|:----|
|
| 126 |
-
| Word count | 1 |
|
| 127 |
|
| 128 |
| Label | Training Sample Count |
|
| 129 |
|:---------|:----------------------|
|
| 130 |
-
| negative |
|
| 131 |
-
| positive |
|
| 132 |
|
| 133 |
### Training Hyperparameters
|
| 134 |
- batch_size: (32, 32)
|
|
@@ -145,79 +147,79 @@ preds = model("التشكيك بصدق باسيل التشكيك بصدق الس
|
|
| 145 |
- warmup_proportion: 0.1
|
| 146 |
- l2_weight: 0.01
|
| 147 |
- seed: 42
|
| 148 |
-
- run_name:
|
| 149 |
- eval_max_steps: -1
|
| 150 |
- load_best_model_at_end: False
|
| 151 |
|
| 152 |
### Training Results
|
| 153 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 154 |
|:------:|:----:|:-------------:|:---------------:|
|
| 155 |
-
| 0.0003 | 1 | 0.
|
| 156 |
-
| 0.0333 | 100 | 0.
|
| 157 |
-
| 0.0667 | 200 | 0.
|
| 158 |
-
| 0.1 | 300 | 0.
|
| 159 |
-
| 0.1333 | 400 | 0.
|
| 160 |
-
| 0.1667 | 500 | 0.
|
| 161 |
-
| 0.2 | 600 | 0.
|
| 162 |
-
| 0.2333 | 700 | 0.
|
| 163 |
-
| 0.2667 | 800 | 0.
|
| 164 |
-
| 0.3 | 900 | 0.
|
| 165 |
-
| 0.3333 | 1000 | 0.
|
| 166 |
-
| 0.3667 | 1100 | 0.
|
| 167 |
-
| 0.4 | 1200 | 0.
|
| 168 |
-
| 0.4333 | 1300 | 0.
|
| 169 |
-
| 0.4667 | 1400 | 0.
|
| 170 |
-
| 0.5 | 1500 | 0.
|
| 171 |
-
| 0.5333 | 1600 | 0.
|
| 172 |
-
| 0.5667 | 1700 | 0.
|
| 173 |
-
| 0.6 | 1800 | 0.
|
| 174 |
-
| 0.6333 | 1900 | 0.
|
| 175 |
-
| 0.6667 | 2000 | 0.
|
| 176 |
-
| 0.7 | 2100 | 0.
|
| 177 |
-
| 0.7333 | 2200 | 0.
|
| 178 |
-
| 0.7667 | 2300 | 0.
|
| 179 |
-
| 0.8 | 2400 | 0.
|
| 180 |
-
| 0.8333 | 2500 | 0.
|
| 181 |
-
| 0.8667 | 2600 | 0.
|
| 182 |
-
| 0.9 | 2700 | 0.
|
| 183 |
-
| 0.9333 | 2800 | 0.
|
| 184 |
-
| 0.9667 | 2900 | 0.
|
| 185 |
-
| 1.0 | 3000 | 0.
|
| 186 |
-
| 1.0333 | 3100 | 0.
|
| 187 |
-
| 1.0667 | 3200 | 0.
|
| 188 |
-
| 1.1 | 3300 | 0.
|
| 189 |
-
| 1.1333 | 3400 | 0.
|
| 190 |
-
| 1.1667 | 3500 | 0.
|
| 191 |
-
| 1.2 | 3600 | 0.
|
| 192 |
-
| 1.2333 | 3700 | 0.
|
| 193 |
-
| 1.2667 | 3800 | 0.
|
| 194 |
-
| 1.3 | 3900 | 0.
|
| 195 |
-
| 1.3333 | 4000 | 0.
|
| 196 |
-
| 1.3667 | 4100 | 0.
|
| 197 |
-
| 1.4 | 4200 | 0.
|
| 198 |
-
| 1.4333 | 4300 | 0.
|
| 199 |
-
| 1.4667 | 4400 | 0.
|
| 200 |
-
| 1.5 | 4500 | 0.
|
| 201 |
-
| 1.5333 | 4600 | 0.
|
| 202 |
-
| 1.5667 | 4700 | 0.
|
| 203 |
-
| 1.6 | 4800 | 0.
|
| 204 |
-
| 1.6333 | 4900 | 0.
|
| 205 |
-
| 1.6667 | 5000 | 0.
|
| 206 |
-
| 1.7 | 5100 | 0.
|
| 207 |
-
| 1.7333 | 5200 | 0.
|
| 208 |
-
| 1.7667 | 5300 | 0.
|
| 209 |
-
| 1.8 | 5400 | 0.
|
| 210 |
-
| 1.8333 | 5500 | 0.
|
| 211 |
-
| 1.8667 | 5600 | 0.
|
| 212 |
-
| 1.9 | 5700 | 0.
|
| 213 |
-
| 1.9333 | 5800 | 0.
|
| 214 |
-
| 1.9667 | 5900 | 0.
|
| 215 |
-
| 2.0 | 6000 | 0.
|
| 216 |
|
| 217 |
### Framework Versions
|
| 218 |
- Python: 3.10.14
|
| 219 |
- SetFit: 1.2.0.dev0
|
| 220 |
-
- Sentence Transformers: 3.
|
| 221 |
- Transformers: 4.45.1
|
| 222 |
- PyTorch: 2.4.0
|
| 223 |
- Datasets: 3.0.1
|
|
|
|
| 10 |
- text-classification
|
| 11 |
- generated_from_setfit_trainer
|
| 12 |
widget:
|
| 13 |
+
- text: عيب يا كلبة لما تجيبي سيرة مصر وتقولي عليها شعب فقير ومشرد يا لبنانيين يا
|
| 14 |
+
انجاس, فعلا ده انتو شعب كلاب
|
| 15 |
+
- text: قوية
|
| 16 |
+
- text: '#لو_ينقطع_المكياج
|
| 17 |
+
|
| 18 |
+
اتوقع في هالزمن الذكور اللي بيبكون عليه مو البنات😂😂'
|
| 19 |
+
- text: كول هوا وسد بوزك معلمك لجاسوس لمجرم بدو شد شعر لشايب
|
| 20 |
+
- text: هاد سعودي ، وانت خليك بحالك يا سوري ولا انت تقليد سوري
|
| 21 |
inference: true
|
| 22 |
model-index:
|
| 23 |
- name: SetFit with akhooli/sbert_ar_nli_500k_ubc_norm
|
|
|
|
| 31 |
split: test
|
| 32 |
metrics:
|
| 33 |
- type: accuracy
|
| 34 |
+
value: 0.858508604206501
|
| 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 |
+
| negative | <ul><li>'نحن نثق بال قضاء اللبناني'</li><li>'مابين السطور.....\nالمنطقة الآمنة ستكون منطقة آمنة برعاية أمريكية لحماية الأكراد من تركيا.....'</li><li>'لم يكن خطاب الوزير جبران باسيل في إفتتاح القمة الإقتصادية بمستوى تطلعات اللبنانيين فبدل أن يركز لإطلاع الوفود على ما يع...'</li></ul> |
|
| 69 |
+
| positive | <ul><li>'هيدا العلم صار مماسح للصرامي انت عايشه بكوكب تاني حالتك بالويل الشهره مش هيك وحياتك لما بتك...'</li><li>'سليل الحسب فعلا سليل الجحش ابن الجحش ابن الوحش سليله حيونه بامتياز'</li><li>'سارقا من عند اومك مش شايف قديش بتشبها هيدي كانت تقعدك عليها لما تعزب يا نوتي ونسيت قلك كول هوا'</li></ul> |
|
| 70 |
|
| 71 |
## Evaluation
|
| 72 |
|
| 73 |
### Metrics
|
| 74 |
| Label | Accuracy |
|
| 75 |
|:--------|:---------|
|
| 76 |
+
| **all** | 0.8585 |
|
| 77 |
|
| 78 |
## Uses
|
| 79 |
|
|
|
|
| 93 |
# Download from the 🤗 Hub
|
| 94 |
model = SetFitModel.from_pretrained("akhooli/setfit_ar_ubc_hs")
|
| 95 |
# Run inference
|
| 96 |
+
preds = model("قوية")
|
| 97 |
```
|
| 98 |
|
| 99 |
<!--
|
|
|
|
| 125 |
### Training Set Metrics
|
| 126 |
| Training set | Min | Median | Max |
|
| 127 |
|:-------------|:----|:--------|:----|
|
| 128 |
+
| Word count | 1 | 14.4687 | 102 |
|
| 129 |
|
| 130 |
| Label | Training Sample Count |
|
| 131 |
|:---------|:----------------------|
|
| 132 |
+
| negative | 2669 |
|
| 133 |
+
| positive | 3200 |
|
| 134 |
|
| 135 |
### Training Hyperparameters
|
| 136 |
- batch_size: (32, 32)
|
|
|
|
| 147 |
- warmup_proportion: 0.1
|
| 148 |
- l2_weight: 0.01
|
| 149 |
- seed: 42
|
| 150 |
+
- run_name: setfit_hate_32kv8
|
| 151 |
- eval_max_steps: -1
|
| 152 |
- load_best_model_at_end: False
|
| 153 |
|
| 154 |
### Training Results
|
| 155 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 156 |
|:------:|:----:|:-------------:|:---------------:|
|
| 157 |
+
| 0.0003 | 1 | 0.3058 | - |
|
| 158 |
+
| 0.0333 | 100 | 0.2672 | - |
|
| 159 |
+
| 0.0667 | 200 | 0.2144 | - |
|
| 160 |
+
| 0.1 | 300 | 0.1601 | - |
|
| 161 |
+
| 0.1333 | 400 | 0.1131 | - |
|
| 162 |
+
| 0.1667 | 500 | 0.0806 | - |
|
| 163 |
+
| 0.2 | 600 | 0.0571 | - |
|
| 164 |
+
| 0.2333 | 700 | 0.0382 | - |
|
| 165 |
+
| 0.2667 | 800 | 0.0261 | - |
|
| 166 |
+
| 0.3 | 900 | 0.0241 | - |
|
| 167 |
+
| 0.3333 | 1000 | 0.0187 | - |
|
| 168 |
+
| 0.3667 | 1100 | 0.0134 | - |
|
| 169 |
+
| 0.4 | 1200 | 0.0155 | - |
|
| 170 |
+
| 0.4333 | 1300 | 0.0128 | - |
|
| 171 |
+
| 0.4667 | 1400 | 0.0114 | - |
|
| 172 |
+
| 0.5 | 1500 | 0.0083 | - |
|
| 173 |
+
| 0.5333 | 1600 | 0.0076 | - |
|
| 174 |
+
| 0.5667 | 1700 | 0.007 | - |
|
| 175 |
+
| 0.6 | 1800 | 0.006 | - |
|
| 176 |
+
| 0.6333 | 1900 | 0.0065 | - |
|
| 177 |
+
| 0.6667 | 2000 | 0.0037 | - |
|
| 178 |
+
| 0.7 | 2100 | 0.0039 | - |
|
| 179 |
+
| 0.7333 | 2200 | 0.0029 | - |
|
| 180 |
+
| 0.7667 | 2300 | 0.0024 | - |
|
| 181 |
+
| 0.8 | 2400 | 0.003 | - |
|
| 182 |
+
| 0.8333 | 2500 | 0.0023 | - |
|
| 183 |
+
| 0.8667 | 2600 | 0.0018 | - |
|
| 184 |
+
| 0.9 | 2700 | 0.0022 | - |
|
| 185 |
+
| 0.9333 | 2800 | 0.0021 | - |
|
| 186 |
+
| 0.9667 | 2900 | 0.003 | - |
|
| 187 |
+
| 1.0 | 3000 | 0.002 | - |
|
| 188 |
+
| 1.0333 | 3100 | 0.0019 | - |
|
| 189 |
+
| 1.0667 | 3200 | 0.0022 | - |
|
| 190 |
+
| 1.1 | 3300 | 0.0015 | - |
|
| 191 |
+
| 1.1333 | 3400 | 0.0013 | - |
|
| 192 |
+
| 1.1667 | 3500 | 0.0013 | - |
|
| 193 |
+
| 1.2 | 3600 | 0.0011 | - |
|
| 194 |
+
| 1.2333 | 3700 | 0.0008 | - |
|
| 195 |
+
| 1.2667 | 3800 | 0.001 | - |
|
| 196 |
+
| 1.3 | 3900 | 0.0006 | - |
|
| 197 |
+
| 1.3333 | 4000 | 0.0013 | - |
|
| 198 |
+
| 1.3667 | 4100 | 0.0008 | - |
|
| 199 |
+
| 1.4 | 4200 | 0.0016 | - |
|
| 200 |
+
| 1.4333 | 4300 | 0.0005 | - |
|
| 201 |
+
| 1.4667 | 4400 | 0.0009 | - |
|
| 202 |
+
| 1.5 | 4500 | 0.0009 | - |
|
| 203 |
+
| 1.5333 | 4600 | 0.0008 | - |
|
| 204 |
+
| 1.5667 | 4700 | 0.0008 | - |
|
| 205 |
+
| 1.6 | 4800 | 0.001 | - |
|
| 206 |
+
| 1.6333 | 4900 | 0.0008 | - |
|
| 207 |
+
| 1.6667 | 5000 | 0.0006 | - |
|
| 208 |
+
| 1.7 | 5100 | 0.0002 | - |
|
| 209 |
+
| 1.7333 | 5200 | 0.0006 | - |
|
| 210 |
+
| 1.7667 | 5300 | 0.0006 | - |
|
| 211 |
+
| 1.8 | 5400 | 0.0004 | - |
|
| 212 |
+
| 1.8333 | 5500 | 0.0005 | - |
|
| 213 |
+
| 1.8667 | 5600 | 0.0005 | - |
|
| 214 |
+
| 1.9 | 5700 | 0.0006 | - |
|
| 215 |
+
| 1.9333 | 5800 | 0.0003 | - |
|
| 216 |
+
| 1.9667 | 5900 | 0.0001 | - |
|
| 217 |
+
| 2.0 | 6000 | 0.0005 | - |
|
| 218 |
|
| 219 |
### Framework Versions
|
| 220 |
- Python: 3.10.14
|
| 221 |
- SetFit: 1.2.0.dev0
|
| 222 |
+
- Sentence Transformers: 3.3.0
|
| 223 |
- Transformers: 4.45.1
|
| 224 |
- PyTorch: 2.4.0
|
| 225 |
- Datasets: 3.0.1
|
config_sentence_transformers.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"__version__": {
|
| 3 |
-
"sentence_transformers": "3.
|
| 4 |
"transformers": "4.45.1",
|
| 5 |
"pytorch": "2.4.0"
|
| 6 |
},
|
| 7 |
"prompts": {},
|
| 8 |
"default_prompt_name": null,
|
| 9 |
-
"similarity_fn_name":
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.3.0",
|
| 4 |
"transformers": "4.45.1",
|
| 5 |
"pytorch": "2.4.0"
|
| 6 |
},
|
| 7 |
"prompts": {},
|
| 8 |
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": "cosine"
|
| 10 |
}
|
config_setfit.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"normalize_embeddings": false,
|
| 3 |
"labels": [
|
| 4 |
"negative",
|
| 5 |
"positive"
|
| 6 |
-
]
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"labels": [
|
| 3 |
"negative",
|
| 4 |
"positive"
|
| 5 |
+
],
|
| 6 |
+
"normalize_embeddings": false
|
| 7 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 651387752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d800e7c8a27b73181e7f6df710acbde52f4b6956a1edb36eff6a02b3cf88615f
|
| 3 |
size 651387752
|
model_head.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7007
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e177df92ba3570bf913cf1d18db428f3a3c43e9e0665075967438540251c642
|
| 3 |
size 7007
|