Push model using huggingface_hub.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

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

README.md

@@ -0,0 +1,238 @@
+---
+base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+library_name: setfit
+metrics:
+- f1
+pipeline_tag: text-classification
+tags:
+- setfit
+- absa
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: Locale:Locale molto bene arredato, con stile e atmosfera tipica valtellinese.
+    Cucina ottima, dal bastone di carne al pesce, dai pizzoccheri agli gnocchetti,
+    dal vino ai dolci,  tutto perfetto e soprattutto di grande qualità... Filippo
+    poi è un’autentica forza della natura, molto simpatico, cordiale e amichevole,...Altro
+- text: cucina:Locale accogliente e familiare...bravissima la ragazza in cucina, come
+    le ragazze al banco e in sala! CONSIGLIATO
+- text: servizio:Il servizio era impeccabile e il tortello di zucca era sublime.
+- text: cucina:Il ristorante propone piatti vegetariani che NON sono vegetariani.
+    Dopo aver specificato al servizio la nostra etica alimentare, ci è stata consigliata
+    una portata che durante la consumazione abbiamo constatato con amarezza che avesse
+    parti di maiale come ingredienti (confermato dalla cucina). Poco valgono le...scuse
+    del servizio, trovo assurdo e inconcepibile che situazioni del genere possano
+    accadere nel 2024. Evidentemente questo è indice della poca professionalità di
+    questo ristorante.Altro
+- text: servizio:La polenta con formaggio era saporita, ma il servizio è stato lento.
+inference: false
+model-index:
+- name: SetFit Aspect Model with sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: f1
+      value: 0.8096514745308312
+      name: F1
+---
+
+# SetFit Aspect Model with sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) as the Sentence Transformer embedding model. A [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance is used for classification. In particular, this model is in charge of filtering aspect span candidates.
+
+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.
+
+This model was trained within the context of a larger system for ABSA, which looks like so:
+
+1. Use a spaCy model to select possible aspect span candidates.
+2. **Use this SetFit model to filter these possible aspect span candidates.**
+3. Use a SetFit model to classify the filtered aspect span candidates.
+
+## Model Details
+
+### Model Description
+- **Model Type:** SetFit
+- **Sentence Transformer body:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2)
+- **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance
+- **spaCy Model:** it_core_news_lg
+- **SetFitABSA Aspect Model:** [MattiaTintori/Final_aspect_Colab_It](https://huggingface.co/MattiaTintori/Final_aspect_Colab_It)
+- **SetFitABSA Polarity Model:** [setfit-absa-polarity](https://huggingface.co/setfit-absa-polarity)
+- **Maximum Sequence Length:** 128 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                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+|:----------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| aspect    | <ul><li>"tavolo:Purtroppo tutte le volte, ed è anni, che tento di prenotare non sono mai stato fortunato........devo dirvi che ora ho un po' perso la poesia!!!!!! O aggiungono tavoli o cambiano location......mai fatta cosi tanta fatica per trovare un tavolo!!!!! Non so francamente se comporro' ancora...Altro"</li><li>'spesa:Devo premettere che sono sempre stato ospite e non so la spesa.Da quanto posso intuire la carne la fa da padrona ed essendo io ve non posso giudicare.Per me trovo sempre cose piacevoli come antipasti a buffet,primi veg riso alle verdure, trofie al pesto patate...Altro'</li><li>'carne:Devo premettere che sono sempre stato ospite e non so la spesa.Da quanto posso intuire la carne la fa da padrona ed essendo io ve non posso giudicare.Per me trovo sempre cose piacevoli come antipasti a buffet,primi veg riso alle verdure, trofie al pesto patate...Altro'</li></ul>                                                  |
+| no aspect | <ul><li>"volte:Purtroppo tutte le volte, ed è anni, che tento di prenotare non sono mai stato fortunato........devo dirvi che ora ho un po' perso la poesia!!!!!! O aggiungono tavoli o cambiano location......mai fatta cosi tanta fatica per trovare un tavolo!!!!! Non so francamente se comporro' ancora...Altro"</li><li>"anni:Purtroppo tutte le volte, ed è anni, che tento di prenotare non sono mai stato fortunato........devo dirvi che ora ho un po' perso la poesia!!!!!! O aggiungono tavoli o cambiano location......mai fatta cosi tanta fatica per trovare un tavolo!!!!! Non so francamente se comporro' ancora...Altro"</li><li>"poesia:Purtroppo tutte le volte, ed è anni, che tento di prenotare non sono mai stato fortunato........devo dirvi che ora ho un po' perso la poesia!!!!!! O aggiungono tavoli o cambiano location......mai fatta cosi tanta fatica per trovare un tavolo!!!!! Non so francamente se comporro' ancora...Altro"</li></ul> |
+
+## Evaluation
+
+### Metrics
+| Label   | F1     |
+|:--------|:-------|
+| **all** | 0.8097 |
+
+## 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 AbsaModel
+
+# Download from the 🤗 Hub
+model = AbsaModel.from_pretrained(
+    "MattiaTintori/Final_aspect_Colab_It",
+    "setfit-absa-polarity",
+)
+# Run inference
+preds = model("The food was great, but the venue is just way too busy.")
+```
+
+<!--
+### 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   | 9   | 40.3192 | 137 |
+
+| Label     | Training Sample Count |
+|:----------|:----------------------|
+| no aspect | 1379                  |
+| aspect    | 1378                  |
+
+### Training Hyperparameters
+- batch_size: (128, 32)
+- num_epochs: (5, 32)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 10
+- body_learning_rate: (5e-05, 5e-05)
+- head_learning_rate: 0.01
+- loss: CosineSimilarityLoss
+- distance_metric: cosine_distance
+- margin: 0.25
+- end_to_end: False
+- use_amp: True
+- warmup_proportion: 0.1
+- l2_weight: 0.02
+- seed: 42
+- eval_max_steps: -1
+- load_best_model_at_end: True
+
+### Training Results
+| Epoch      | Step    | Training Loss | Validation Loss |
+|:----------:|:-------:|:-------------:|:---------------:|
+| 0.0023     | 1       | 0.2484        | -               |
+| 0.0464     | 20      | 0.2718        | 0.259           |
+| 0.0928     | 40      | 0.2581        | 0.2544          |
+| 0.1392     | 60      | 0.2266        | 0.2475          |
+| 0.1856     | 80      | 0.233         | 0.2298          |
+| 0.2320     | 100     | 0.2104        | 0.2145          |
+| **0.2784** | **120** | **0.1487**    | **0.2106**      |
+| 0.3248     | 140     | 0.1615        | 0.2314          |
+| 0.3712     | 160     | 0.1328        | 0.2164          |
+| 0.4176     | 180     | 0.0905        | 0.2164          |
+| 0.4640     | 200     | 0.0934        | 0.2517          |
+| 0.5104     | 220     | 0.0942        | 0.2185          |
+| 0.5568     | 240     | 0.0774        | 0.2469          |
+| 0.6032     | 260     | 0.1013        | 0.2248          |
+| 0.6497     | 280     | 0.0781        | 0.2221          |
+| 0.6961     | 300     | 0.0386        | 0.2362          |
+| 0.7425     | 320     | 0.084         | 0.2386          |
+
+* The bold row denotes the saved checkpoint.
+### Framework Versions
+- Python: 3.10.12
+- SetFit: 1.0.3
+- Sentence Transformers: 3.1.0
+- spaCy: 3.7.6
+- Transformers: 4.39.0
+- PyTorch: 2.4.0+cu121
+- Datasets: 3.0.0
+- 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.*
+-->

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "checkpoints/step_120",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.0",
+    "transformers": "4.39.0",
+    "pytorch": "2.4.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

config_setfit.json

@@ -0,0 +1,9 @@
+{
+  "labels": [
+    "no aspect",
+    "aspect"
+  ],
+  "span_context": 0,
+  "spacy_model": "it_core_news_lg",
+  "normalize_embeddings": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d7562656c94f845bd0e3d3ab4a6af2d18afe0121ad2f04476ba9892831296c
+size 1112197096

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca6599d277cbdd7a1a332c4e3ae54464d35b4e31b449a85cef84a7cde9203a9
+size 7706

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa685fc160bbdbab64058d4fc91b60e62d207e8dc60b9af5c002c5ab946ded00
+size 17083009

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}