Push model using huggingface_hub.

README.md

@@ -8,11 +8,11 @@ tags:
 metrics:
 - accuracy
 widget:
-- text: suck me
-- text: I love to read
-- text: or a girlfriend
-- text: What is your gender?
-- text: romantic
+- text: The skull protects the brain and eyes.
+- text: to her sex
+- text: play hide and seek
+- text: I was before
+- text: 'no'
 pipeline_tag: text-classification
 inference: true
 base_model: BAAI/bge-base-en-v1.5
@@ -28,7 +28,7 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.7419354838709677
+      value: 1.0
       name: Accuracy
 ---
 
@@ -60,17 +60,17 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label | Examples                                                                                                       |
-|:------|:---------------------------------------------------------------------------------------------------------------|
-| other | <ul><li>"I'm going to be the flight attendant"</li><li>'Writing dancing and singing'</li><li>'Girls'</li></ul> |
-| sex   | <ul><li>'Sex'</li><li>'i find it on the pronoun list'</li><li>'I was hot'</li></ul>                            |
+| Label | Examples                                                                                                     |
+|:------|:-------------------------------------------------------------------------------------------------------------|
+| sex   | <ul><li>'I like to suck cock'</li><li>'suck me'</li><li>'What happens when you ride a human being'</li></ul> |
+| other | <ul><li>'ok'</li><li>'Can I ask a question?'</li><li>'THANK YOU'</li></ul>                                   |
 
 ## Evaluation
 
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.7419   |
+| **all** | 1.0      |
 
 ## Uses
 
@@ -90,7 +90,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("setfit_model_id")
 # Run inference
-preds = model("suck me")
+preds = model("no")
 ```
 
 <!--
@@ -122,16 +122,16 @@ preds = model("suck me")
 ### Training Set Metrics
 | Training set | Min | Median | Max |
 |:-------------|:----|:-------|:----|
-| Word count   | 1   | 5.8906 | 26  |
+| Word count   | 1   | 5.9314 | 29  |
 
 | Label | Training Sample Count |
 |:------|:----------------------|
-| other | 32                    |
-| sex   | 32                    |
+| other | 48                    |
+| sex   | 54                    |
 
 ### Training Hyperparameters
 - batch_size: (32, 32)
-- num_epochs: (10, 10)
+- num_epochs: (2, 2)
 - max_steps: -1
 - sampling_strategy: oversampling
 - body_learning_rate: (2e-05, 1e-05)
@@ -149,20 +149,13 @@ preds = model("suck me")
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0152 | 1    | 0.2459        | -               |
-| 0.7576 | 50   | 0.2101        | -               |
-| 1.5152 | 100  | 0.007         | -               |
-| 2.2727 | 150  | 0.0031        | -               |
-| 3.0303 | 200  | 0.0028        | -               |
-| 3.7879 | 250  | 0.0021        | -               |
-| 4.5455 | 300  | 0.0024        | -               |
-| 5.3030 | 350  | 0.0017        | -               |
-| 6.0606 | 400  | 0.002         | -               |
-| 6.8182 | 450  | 0.0018        | -               |
-| 7.5758 | 500  | 0.0018        | -               |
-| 8.3333 | 550  | 0.0017        | -               |
-| 9.0909 | 600  | 0.0017        | -               |
-| 9.8485 | 650  | 0.0016        | -               |
+| 0.0060 | 1    | 0.2346        | -               |
+| 0.2994 | 50   | 0.1766        | -               |
+| 0.5988 | 100  | 0.0068        | -               |
+| 0.8982 | 150  | 0.0033        | -               |
+| 1.1976 | 200  | 0.0032        | -               |
+| 1.4970 | 250  | 0.0027        | -               |
+| 1.7964 | 300  | 0.0025        | -               |
 
 ### Framework Versions
 - Python: 3.9.6

config_setfit.json

@@ -1,7 +1,7 @@
 {
-  "normalize_embeddings": false,
   "labels": [
     "other",
     "sex"
-  ]
+  ],
+  "normalize_embeddings": false
 }

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc868c1e097ab2d72a081c5813ee86e1cd6f496552b7dfd88544edc9de2a4d0
+oid sha256:83b2e42fefab5d12cbc59b9aec69006c9376a07089aca60ffdb0a4875f27aa37
 size 6991

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d3d44eae1b903e72fd0918c84a5bb10094c755f4b8f7f69f5f570cdcf0f619
+oid sha256:3bd38f910e41b49cf82bcef489120425f9467b3136e21db5d6c8f0c0c23ac482
 size 437997357