fix: changed CMD in dokckerfile

.gitignore

@@ -0,0 +1,4 @@
+.env
+.venv/
+env/
+venv/

app.py

@@ -1,5 +1,6 @@
 from fastapi import FastAPI, Request
 from pydantic import BaseModel
+from setfit import SetFitModel
 
 app = FastAPI()
 
@@ -12,9 +13,9 @@ class LabelScore(BaseModel):
 
 @app.post("/predict", response_model=LabelScore)
 async def predict(input: TextInput):
-    label = "positive" if "good" in input.text else "negative"
-    score = 0.9 if label == "positive" else 0.1
-    return {"label": label, "score": score}
+    model = SetFitModel.from_pretrained("assets")
+    preds = model.predict(input)
+    return preds
 
 @app.get("/")
 def read_root():

assets/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

assets/README.md

@@ -0,0 +1,204 @@
+---
+library_name: setfit
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+base_model: BAAI/bge-base-en-v1.5
+metrics:
+- accuracy
+widget:
+- text: Dear GO FIRST Flyer, Comply with web-check in & state regulations on www.FlyGoFirst.com/wci.
+    Power banks are allowed ONLY in cabin baggage and NOT in check-in baggage.
+- text: INR 415000.00 debited from DBS a/c no. ********1417 on 09-04-2022 to mishra
+    ji via NEFT (UTR Ref No 0811OP2104023743) will reach bene a/c usually within 2
+    hours.
+- text: Your plan Rs 719-3m-2GB/D for Jio Number 8076716202 has expired on 12-Feb-23
+    22:24 Hrs. To continue enjoying Jio services, recharge immediately.  To recharge,
+    click https://www.jio.com/selfcare/recharge Dial 1991, to know your current balance,
+    validity, plan details and for exciting recharge plans.
+- text: 'HDFC Bank: Rs 72.00 debited from a/c **0591 on 16-10-21 to VPA gpay-11169632313@okbizaxis(UPI
+    Ref No 128968285337). Not you? Call on 18002586161 to report'
+- text: 'Get up to Rs.1K assured cashback & Rs.25K free credit with OlaMoney Postpaid+.
+    Use it across 15K+ apps, pay back in 30 days. Click : https://hello.ola.app/ompps'
+pipeline_tag: text-classification
+inference: true
+model-index:
+- name: SetFit with BAAI/bge-base-en-v1.5
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.9576271186440678
+      name: Accuracy
+---
+
+# SetFit with BAAI/bge-base-en-v1.5
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
+
+The model has been trained using an efficient few-shot learning technique that involves:
+
+1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
+2. Training a classification head with features from the fine-tuned Sentence Transformer.
+
+## Model Details
+
+### Model Description
+- **Model Type:** SetFit
+- **Sentence Transformer body:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 512 tokens
+- **Number of Classes:** 2 classes
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
+- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
+- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
+
+### Model Labels
+| Label       | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+|:------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| Offer       | <ul><li>'Exclusive offer only for you.Recharge with Rs.49 to get 100min voice call,1GB data for 15 days.Hurry,recharge today.'</li><li>'Abhi *911# milaa kr payen Rs.25 advance loan aur phir *51# dial kren aur Rs. 10+T mei haasil kren, 500 MB aur 50 Zong Minutes puray din kay liye'</li><li>'HDFC BANK PERSONAL L0AN  IndependenceDay offer 10.25% 0%PF  FRESH LOAN / TOPUP LOAN / PARALLEL LOAN/BT  Hurry! Apply - 8095227619  T&C* '</li></ul>                                                                                                                                                                                                                                       |
+| Transaction | <ul><li>'Dear Customer, your DBS account no ********1417 is credited with INR 25000 on 01-10-2021 and is subject to clearance. Current Balance is INR 58661.69.'</li><li>'Pls use IFSC BARB0*** instead of old IFSC VIJB** for remittances as old code will be discontinued wef 01.07.2021. Advise your remitters also-Bank of Baroda'</li><li>'Your Stock broker ZERODHA BROKING LIMITED. reported your fund balance Rs.26986.54 & securities balance 0 as on end of 09-oct-2021. Balances do not cover your bank, DP & PMS balance with broking entity. Check details at [email protected]. If email Id not correct, kindly update with your broker - National Stock Exchange'</li></ul> |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.9576   |
+
+## Uses
+
+### Direct Use for Inference
+
+First install the SetFit library:
+
+```bash
+pip install setfit
+```
+
+Then you can load this model and run inference.
+
+```python
+from setfit import SetFitModel
+
+# Download from the 🤗 Hub
+model = SetFitModel.from_pretrained("setfit_model_id")
+# Run inference
+preds = model("HDFC Bank: Rs 72.00 debited from a/c **0591 on 16-10-21 to VPA gpay-11169632313@okbizaxis(UPI Ref No 128968285337). Not you? Call on 18002586161 to report")
+```
+
+<!--
+### Downstream Use
+
+*List how someone could finetune this model on their own dataset.*
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Set Metrics
+| Training set | Min | Median  | Max |
+|:-------------|:----|:--------|:----|
+| Word count   | 3   | 26.7702 | 135 |
+
+| Label       | Training Sample Count |
+|:------------|:----------------------|
+| Transaction | 103                   |
+| Offer       | 132                   |
+
+### Training Hyperparameters
+- batch_size: (16, 16)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 1
+- body_learning_rate: (2e-05, 1e-05)
+- head_learning_rate: 0.01
+- loss: CosineSimilarityLoss
+- distance_metric: cosine_distance
+- margin: 0.25
+- end_to_end: False
+- use_amp: False
+- warmup_proportion: 0.1
+- seed: 42
+- eval_max_steps: -1
+- load_best_model_at_end: False
+
+### Training Results
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0333 | 1    | 0.2366        | -               |
+
+### Framework Versions
+- Python: 3.11.9
+- SetFit: 1.0.3
+- Sentence Transformers: 3.0.1
+- Transformers: 4.39.0
+- PyTorch: 2.3.1+cu121
+- Datasets: 2.19.2
+- Tokenizers: 0.15.2
+
+## Citation
+
+### BibTeX
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2209.11055,
+    doi = {10.48550/ARXIV.2209.11055},
+    url = {https://arxiv.org/abs/2209.11055},
+    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
+    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
+    title = {Efficient Few-Shot Learning Without Prompts},
+    publisher = {arXiv},
+    year = {2022},
+    copyright = {Creative Commons Attribution 4.0 International}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

assets/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

assets/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.39.0",
+    "pytorch": "2.3.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

assets/config_setfit.json

@@ -0,0 +1,7 @@
+{
+  "normalize_embeddings": false,
+  "labels": [
+    "Transaction",
+    "Offer"
+  ]
+}

assets/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c926e4aa2d85d6628ea5999d939101b09bdf1910525b3a3c112b4bcf014c21d
+size 437951328

assets/model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9ed00840d3def363cf16611f73da64fd36ce69e4a6474132e615013eb4333f
+size 7087

assets/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

assets/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

assets/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

assets/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}