Push model using huggingface_hub.
Browse files- README.md +125 -77
- config_sentence_transformers.json +1 -1
- model.safetensors +1 -1
- model_head.pkl +1 -1
README.md
CHANGED
|
@@ -10,15 +10,13 @@ tags:
|
|
| 10 |
- text-classification
|
| 11 |
- generated_from_setfit_trainer
|
| 12 |
widget:
|
| 13 |
-
- text:
|
| 14 |
-
|
| 15 |
-
- text:
|
| 16 |
-
|
| 17 |
-
- text:
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
- text: كول هوا خسرتو بأرضك وبين جمهورك بعد ما منعت القطريين من تشجيع جمهورهم انتو
|
| 21 |
-
فاشلين في كل شئ وهم متفوقين عليكم في...
|
| 22 |
inference: true
|
| 23 |
model-index:
|
| 24 |
- name: SetFit with akhooli/sbert_ar_nli_500k_norm
|
|
@@ -32,7 +30,7 @@ model-index:
|
|
| 32 |
split: test
|
| 33 |
metrics:
|
| 34 |
- type: accuracy
|
| 35 |
-
value: 0.
|
| 36 |
name: Accuracy
|
| 37 |
---
|
| 38 |
|
|
@@ -64,17 +62,17 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 64 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 65 |
|
| 66 |
### Model Labels
|
| 67 |
-
| Label | Examples
|
| 68 |
-
|
| 69 |
-
| negative | <ul><li>'
|
| 70 |
-
| positive | <ul><li>'
|
| 71 |
|
| 72 |
## Evaluation
|
| 73 |
|
| 74 |
### Metrics
|
| 75 |
| Label | Accuracy |
|
| 76 |
|:--------|:---------|
|
| 77 |
-
| **all** | 0.
|
| 78 |
|
| 79 |
## Uses
|
| 80 |
|
|
@@ -94,7 +92,7 @@ from setfit import SetFitModel
|
|
| 94 |
# Download from the 🤗 Hub
|
| 95 |
model = SetFitModel.from_pretrained("akhooli/setfit_ar_hs")
|
| 96 |
# Run inference
|
| 97 |
-
preds = model("
|
| 98 |
```
|
| 99 |
|
| 100 |
<!--
|
|
@@ -124,19 +122,19 @@ preds = model("شيل عينك عن لبنان انت و كل كلب متلك ح
|
|
| 124 |
## Training Details
|
| 125 |
|
| 126 |
### Training Set Metrics
|
| 127 |
-
| Training set | Min | Median
|
| 128 |
-
|
| 129 |
-
| Word count | 1 | 12.
|
| 130 |
|
| 131 |
| Label | Training Sample Count |
|
| 132 |
|:---------|:----------------------|
|
| 133 |
-
| negative |
|
| 134 |
-
| positive |
|
| 135 |
|
| 136 |
### Training Hyperparameters
|
| 137 |
- batch_size: (32, 32)
|
| 138 |
- num_epochs: (1, 1)
|
| 139 |
-
- max_steps:
|
| 140 |
- sampling_strategy: undersampling
|
| 141 |
- body_learning_rate: (2e-05, 1e-05)
|
| 142 |
- head_learning_rate: 0.01
|
|
@@ -148,69 +146,119 @@ preds = model("شيل عينك عن لبنان انت و كل كلب متلك ح
|
|
| 148 |
- warmup_proportion: 0.1
|
| 149 |
- l2_weight: 0.01
|
| 150 |
- seed: 42
|
| 151 |
-
- run_name:
|
| 152 |
- eval_max_steps: -1
|
| 153 |
- load_best_model_at_end: False
|
| 154 |
|
| 155 |
### Training Results
|
| 156 |
-
| Epoch | Step
|
| 157 |
-
|
| 158 |
-
| 0.
|
| 159 |
-
| 0.
|
| 160 |
-
| 0.
|
| 161 |
-
| 0.
|
| 162 |
-
| 0.
|
| 163 |
-
| 0.
|
| 164 |
-
| 0.
|
| 165 |
-
| 0.
|
| 166 |
-
| 0.
|
| 167 |
-
| 0.
|
| 168 |
-
| 0.
|
| 169 |
-
| 0.
|
| 170 |
-
| 0.
|
| 171 |
-
| 0.
|
| 172 |
-
| 0.
|
| 173 |
-
| 0.
|
| 174 |
-
| 0.
|
| 175 |
-
| 0.
|
| 176 |
-
| 0.
|
| 177 |
-
| 0.
|
| 178 |
-
| 0.
|
| 179 |
-
| 0.
|
| 180 |
-
| 0.
|
| 181 |
-
| 0.
|
| 182 |
-
| 0.
|
| 183 |
-
|
|
| 184 |
-
|
|
| 185 |
-
|
|
| 186 |
-
|
|
| 187 |
-
|
|
| 188 |
-
|
|
| 189 |
-
|
|
| 190 |
-
|
|
| 191 |
-
|
|
| 192 |
-
|
|
| 193 |
-
|
|
| 194 |
-
|
|
| 195 |
-
|
|
| 196 |
-
|
|
| 197 |
-
|
|
| 198 |
-
|
|
| 199 |
-
|
|
| 200 |
-
|
|
| 201 |
-
|
|
| 202 |
-
|
|
| 203 |
-
|
|
| 204 |
-
|
|
| 205 |
-
|
|
| 206 |
-
|
|
| 207 |
-
|
|
| 208 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 209 |
|
| 210 |
### Framework Versions
|
| 211 |
- Python: 3.10.14
|
| 212 |
- SetFit: 1.2.0.dev0
|
| 213 |
-
- Sentence Transformers: 3.
|
| 214 |
- Transformers: 4.45.1
|
| 215 |
- PyTorch: 2.4.0
|
| 216 |
- Datasets: 3.0.1
|
|
|
|
| 10 |
- text-classification
|
| 11 |
- generated_from_setfit_trainer
|
| 12 |
widget:
|
| 13 |
+
- text: يا زلمة يلي بيصنع معنا معروف بنتشكره شو ما كان يكون وانتم ادعياء الاخوة العرب
|
| 14 |
+
هول مش ايرانيين ولا عجم عرب متلنا متلهم
|
| 15 |
+
- text: لعمي
|
| 16 |
+
- text: هلق رجع لمن قلو الريس تبعو هش قلو مشمو على عيني ؟
|
| 17 |
+
- text: مثل الكليشيه وبشكل يومي في حدا بده يعاير التاني بيقوم بيشبهه بالكلب والله
|
| 18 |
+
اذا حدا شبهني بالكلب بعتبرها مدح شديد
|
| 19 |
+
- text: الله لا يحرمك من الهبل ان شاء الله
|
|
|
|
|
|
|
| 20 |
inference: true
|
| 21 |
model-index:
|
| 22 |
- name: SetFit with akhooli/sbert_ar_nli_500k_norm
|
|
|
|
| 30 |
split: test
|
| 31 |
metrics:
|
| 32 |
- type: accuracy
|
| 33 |
+
value: 0.8497652582159625
|
| 34 |
name: Accuracy
|
| 35 |
---
|
| 36 |
|
|
|
|
| 62 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 63 |
|
| 64 |
### Model Labels
|
| 65 |
+
| Label | Examples |
|
| 66 |
+
|:---------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 67 |
+
| negative | <ul><li>'الف تحية لشيخ العقل ومشايخنا الكرام'</li><li>'بتحبو او بتكرهو انشط وزير و رئيس تيار و ديبلوماسيتو بتتدرّس'</li><li>'نعم معاليك ستظل دمشق المدينة التي تغنى بها الشعراء وهذه الكلمات خير شاهد فرشت فوق ثراك الطاهرالهدبا'</li></ul> |
|
| 68 |
+
| positive | <ul><li>'لسانك حصانك وحسنا فعلت قطر لتلغي مركز الأبحاث لا مرحبا بكم انتم ولا تستاهلون اي عمل لكم ناكرين المعروف'</li><li>'ارنب وبضلك ارنب ابكي بترتاح يا صرماية'</li><li>'سليمان فرنجية عبارة عن كلب مسعور لديه حاسة شم ��وية جداً شم ريحة كرسي الرئاسة ولكنه لن يجلس عليها ابداً وتصبحو على خير'</li></ul> |
|
| 69 |
|
| 70 |
## Evaluation
|
| 71 |
|
| 72 |
### Metrics
|
| 73 |
| Label | Accuracy |
|
| 74 |
|:--------|:---------|
|
| 75 |
+
| **all** | 0.8498 |
|
| 76 |
|
| 77 |
## Uses
|
| 78 |
|
|
|
|
| 92 |
# Download from the 🤗 Hub
|
| 93 |
model = SetFitModel.from_pretrained("akhooli/setfit_ar_hs")
|
| 94 |
# Run inference
|
| 95 |
+
preds = model("لعمي")
|
| 96 |
```
|
| 97 |
|
| 98 |
<!--
|
|
|
|
| 122 |
## Training Details
|
| 123 |
|
| 124 |
### Training Set Metrics
|
| 125 |
+
| Training set | Min | Median | Max |
|
| 126 |
+
|:-------------|:----|:--------|:----|
|
| 127 |
+
| Word count | 1 | 12.2323 | 52 |
|
| 128 |
|
| 129 |
| Label | Training Sample Count |
|
| 130 |
|:---------|:----------------------|
|
| 131 |
+
| negative | 1995 |
|
| 132 |
+
| positive | 2500 |
|
| 133 |
|
| 134 |
### Training Hyperparameters
|
| 135 |
- batch_size: (32, 32)
|
| 136 |
- num_epochs: (1, 1)
|
| 137 |
+
- max_steps: 10000
|
| 138 |
- sampling_strategy: undersampling
|
| 139 |
- body_learning_rate: (2e-05, 1e-05)
|
| 140 |
- head_learning_rate: 0.01
|
|
|
|
| 146 |
- warmup_proportion: 0.1
|
| 147 |
- l2_weight: 0.01
|
| 148 |
- seed: 42
|
| 149 |
+
- run_name: setfit_hate_25kv
|
| 150 |
- eval_max_steps: -1
|
| 151 |
- load_best_model_at_end: False
|
| 152 |
|
| 153 |
### Training Results
|
| 154 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 155 |
+
|:------:|:-----:|:-------------:|:---------------:|
|
| 156 |
+
| 0.0002 | 1 | 0.3185 | - |
|
| 157 |
+
| 0.02 | 100 | 0.2901 | - |
|
| 158 |
+
| 0.04 | 200 | 0.2441 | - |
|
| 159 |
+
| 0.06 | 300 | 0.2209 | - |
|
| 160 |
+
| 0.08 | 400 | 0.1715 | - |
|
| 161 |
+
| 0.1 | 500 | 0.1304 | - |
|
| 162 |
+
| 0.12 | 600 | 0.0891 | - |
|
| 163 |
+
| 0.14 | 700 | 0.0604 | - |
|
| 164 |
+
| 0.16 | 800 | 0.0436 | - |
|
| 165 |
+
| 0.18 | 900 | 0.0408 | - |
|
| 166 |
+
| 0.2 | 1000 | 0.0265 | - |
|
| 167 |
+
| 0.22 | 1100 | 0.0239 | - |
|
| 168 |
+
| 0.24 | 1200 | 0.0235 | - |
|
| 169 |
+
| 0.26 | 1300 | 0.0232 | - |
|
| 170 |
+
| 0.28 | 1400 | 0.0241 | - |
|
| 171 |
+
| 0.3 | 1500 | 0.019 | - |
|
| 172 |
+
| 0.32 | 1600 | 0.0168 | - |
|
| 173 |
+
| 0.34 | 1700 | 0.0172 | - |
|
| 174 |
+
| 0.36 | 1800 | 0.0136 | - |
|
| 175 |
+
| 0.38 | 1900 | 0.0099 | - |
|
| 176 |
+
| 0.4 | 2000 | 0.0117 | - |
|
| 177 |
+
| 0.42 | 2100 | 0.0091 | - |
|
| 178 |
+
| 0.44 | 2200 | 0.0067 | - |
|
| 179 |
+
| 0.46 | 2300 | 0.0074 | - |
|
| 180 |
+
| 0.48 | 2400 | 0.0055 | - |
|
| 181 |
+
| 0.5 | 2500 | 0.0053 | - |
|
| 182 |
+
| 0.52 | 2600 | 0.0054 | - |
|
| 183 |
+
| 0.54 | 2700 | 0.0058 | - |
|
| 184 |
+
| 0.56 | 2800 | 0.0059 | - |
|
| 185 |
+
| 0.58 | 2900 | 0.0055 | - |
|
| 186 |
+
| 0.6 | 3000 | 0.0043 | - |
|
| 187 |
+
| 0.62 | 3100 | 0.0045 | - |
|
| 188 |
+
| 0.64 | 3200 | 0.0055 | - |
|
| 189 |
+
| 0.66 | 3300 | 0.0042 | - |
|
| 190 |
+
| 0.68 | 3400 | 0.0024 | - |
|
| 191 |
+
| 0.7 | 3500 | 0.0025 | - |
|
| 192 |
+
| 0.72 | 3600 | 0.0047 | - |
|
| 193 |
+
| 0.74 | 3700 | 0.0036 | - |
|
| 194 |
+
| 0.76 | 3800 | 0.0029 | - |
|
| 195 |
+
| 0.78 | 3900 | 0.0043 | - |
|
| 196 |
+
| 0.8 | 4000 | 0.0036 | - |
|
| 197 |
+
| 0.82 | 4100 | 0.0025 | - |
|
| 198 |
+
| 0.84 | 4200 | 0.0033 | - |
|
| 199 |
+
| 0.86 | 4300 | 0.0018 | - |
|
| 200 |
+
| 0.88 | 4400 | 0.0016 | - |
|
| 201 |
+
| 0.9 | 4500 | 0.0018 | - |
|
| 202 |
+
| 0.92 | 4600 | 0.0023 | - |
|
| 203 |
+
| 0.94 | 4700 | 0.0027 | - |
|
| 204 |
+
| 0.96 | 4800 | 0.0023 | - |
|
| 205 |
+
| 0.98 | 4900 | 0.0012 | - |
|
| 206 |
+
| 1.0 | 5000 | 0.0021 | - |
|
| 207 |
+
| 1.02 | 5100 | 0.0026 | - |
|
| 208 |
+
| 1.04 | 5200 | 0.0019 | - |
|
| 209 |
+
| 1.06 | 5300 | 0.002 | - |
|
| 210 |
+
| 1.08 | 5400 | 0.0022 | - |
|
| 211 |
+
| 1.1 | 5500 | 0.0025 | - |
|
| 212 |
+
| 1.12 | 5600 | 0.0033 | - |
|
| 213 |
+
| 1.1400 | 5700 | 0.001 | - |
|
| 214 |
+
| 1.16 | 5800 | 0.0016 | - |
|
| 215 |
+
| 1.18 | 5900 | 0.0015 | - |
|
| 216 |
+
| 1.2 | 6000 | 0.0008 | - |
|
| 217 |
+
| 1.22 | 6100 | 0.0011 | - |
|
| 218 |
+
| 1.24 | 6200 | 0.0012 | - |
|
| 219 |
+
| 1.26 | 6300 | 0.0009 | - |
|
| 220 |
+
| 1.28 | 6400 | 0.0012 | - |
|
| 221 |
+
| 1.3 | 6500 | 0.001 | - |
|
| 222 |
+
| 1.32 | 6600 | 0.0014 | - |
|
| 223 |
+
| 1.34 | 6700 | 0.0002 | - |
|
| 224 |
+
| 1.3600 | 6800 | 0.0005 | - |
|
| 225 |
+
| 1.38 | 6900 | 0.0003 | - |
|
| 226 |
+
| 1.4 | 7000 | 0.0001 | - |
|
| 227 |
+
| 1.42 | 7100 | 0.0007 | - |
|
| 228 |
+
| 1.44 | 7200 | 0.0003 | - |
|
| 229 |
+
| 1.46 | 7300 | 0.0002 | - |
|
| 230 |
+
| 1.48 | 7400 | 0.0005 | - |
|
| 231 |
+
| 1.5 | 7500 | 0.0001 | - |
|
| 232 |
+
| 1.52 | 7600 | 0.0003 | - |
|
| 233 |
+
| 1.54 | 7700 | 0.001 | - |
|
| 234 |
+
| 1.56 | 7800 | 0.0003 | - |
|
| 235 |
+
| 1.58 | 7900 | 0.0 | - |
|
| 236 |
+
| 1.6 | 8000 | 0.0002 | - |
|
| 237 |
+
| 1.62 | 8100 | 0.0 | - |
|
| 238 |
+
| 1.6400 | 8200 | 0.0002 | - |
|
| 239 |
+
| 1.6600 | 8300 | 0.0002 | - |
|
| 240 |
+
| 1.6800 | 8400 | 0.0 | - |
|
| 241 |
+
| 1.7 | 8500 | 0.0 | - |
|
| 242 |
+
| 1.72 | 8600 | 0.0002 | - |
|
| 243 |
+
| 1.74 | 8700 | 0.0002 | - |
|
| 244 |
+
| 1.76 | 8800 | 0.0002 | - |
|
| 245 |
+
| 1.78 | 8900 | 0.0002 | - |
|
| 246 |
+
| 1.8 | 9000 | 0.0 | - |
|
| 247 |
+
| 1.8200 | 9100 | 0.0004 | - |
|
| 248 |
+
| 1.8400 | 9200 | 0.0 | - |
|
| 249 |
+
| 1.8600 | 9300 | 0.0002 | - |
|
| 250 |
+
| 1.88 | 9400 | 0.0002 | - |
|
| 251 |
+
| 1.9 | 9500 | 0.0 | - |
|
| 252 |
+
| 1.92 | 9600 | 0.0003 | - |
|
| 253 |
+
| 1.94 | 9700 | 0.0 | - |
|
| 254 |
+
| 1.96 | 9800 | 0.0 | - |
|
| 255 |
+
| 1.98 | 9900 | 0.0 | - |
|
| 256 |
+
| 2.0 | 10000 | 0.0 | - |
|
| 257 |
|
| 258 |
### Framework Versions
|
| 259 |
- Python: 3.10.14
|
| 260 |
- SetFit: 1.2.0.dev0
|
| 261 |
+
- Sentence Transformers: 3.2.1
|
| 262 |
- Transformers: 4.45.1
|
| 263 |
- PyTorch: 2.4.0
|
| 264 |
- Datasets: 3.0.1
|
config_sentence_transformers.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"__version__": {
|
| 3 |
-
"sentence_transformers": "3.
|
| 4 |
"transformers": "4.45.1",
|
| 5 |
"pytorch": "2.4.0"
|
| 6 |
},
|
|
|
|
| 1 |
{
|
| 2 |
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.2.1",
|
| 4 |
"transformers": "4.45.1",
|
| 5 |
"pytorch": "2.4.0"
|
| 6 |
},
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 540795752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a57cf1b94b40775394f2923ab55ef1d19c4834e85d7a2009c4176186c9e237f
|
| 3 |
size 540795752
|
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:d6eeaa6c778128349ddfa446dacb3d93308083b257078b1323aa10159fafc4e0
|
| 3 |
size 7007
|