Update README.md

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
-tags: []
+language:
+- it
 ---
 
 # Model Card for Model ID
@@ -11,189 +12,75 @@ tags: []
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+This repository only contains the adapter of the fine-tuned model! You should have access to the base model in order to load it correctly.
 
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
+### Model Description
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+- **Developed by:** Yuri Noviello
+- **Language(s) (NLP):** Italian
+- **Finetuned from model:** [google/gemma-2b](https://huggingface.co/google/gemma-2b)
 
-[More Information Needed]
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
 
-[More Information Needed]
+| Metric                      | DS |
+|:----------------------------|:----------------------|
+| **Score**     | Score            | 
 
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
+---
 
-[More Information Needed]
+## How to Use
+
+```python
+import torch
+import torch.nn.functional as F
+from torch import Tensor
+from transformers import AutoTokenizer, AutoModel
+
+def last_token_pool(last_hidden_states: Tensor,
+                 attention_mask: Tensor) -> Tensor:
+    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
+    if left_padding:
+        return last_hidden_states[:, -1]
+    else:
+        sequence_lengths = attention_mask.sum(dim=1) - 1
+        batch_size = last_hidden_states.shape[0]
+        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
+
+def get_detailed_instruct(task_description: str, query: str) -> str:
+    return f'{task_description}\nQuery: {query}'
+
+
+model = AutoModel.from_pretrained('yuri-no/gemma-argos', torch_dtype=torch.bfloat16).to('cuda')
+tokenizer = AutoTokenizer.from_pretrained('yuri-no/gemma-argos')
+
+# Each query must come with a one-sentence instruction that describes the task
+task = 'Given a search query, retrieve relevant passages that answer the query'
+queries = [
+    get_detailed_instruct(task, 'In che anno il Napoli ha vinto il suo terzo scudetto?'),
+    get_detailed_instruct(task, 'Quali sono le migliori Università italiane?'),
+]
+# No need to add instruction for retrieval documents
+documents = [
+    "Dopo un'attesa durata 33 anni, il Napoli è Campione d'Italia per la terza volta. Per la certezza aritmetica serviva che non perdesse fuori casa con l'Udinese ed è bastato un pareggio per 1-1, avvenuto con il brivido del gol bianconero firmato da Lovric e poi con il pareggio di Osimhen al 52'. La partita di giovedì 4 maggio 2023, trasmessa anche sui maxi-schermi dello Stadio Maradona, è diventata così così in una grande festa per tutto il popolo napoletano e una pagina indimenticabile nella storia del calcio italiano.",
+    "L’Università di Bologna si conferma ancora una volta tra le migliori d’Italia. Stando a un’analisi delle più autorevoli classifiche universitarie i cui risultati sono stati pubblicati dalla piattaforma di apprendimento Preply, la quale ha esaminato le classifiche accademiche di U.S. News in collaborazione con l'istituto di analisi Clarivate, sono stati analizzati i dieci corsi di laurea più popolari nelle principali città universitarie italiane.",
+    "Il Decreto Legislativo 7 marzo 2005 n. 82 Codice dell'Amministrazione digitale, definisce le pubblicazioni contenute su supporti informatici valide e rilevanti a tutti gli effetti di legge in quanto la riproduzione è effettuata in modo tale da garantire la conformità dei documenti agli atti originali. Cio' al fine di rendere possibile l'esonero della produzione ed esibizione del formato originale su supporto cartaceo quando richiesto ad ogni effetto di legge."
+]
+input_texts = queries + documents
+
+max_length = 512
+# Tokenize the input texts
+batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt').to('cuda')
+
+outputs = model(**batch_dict)
+embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
+
+# normalize embeddings
+embeddings = F.normalize(embeddings, p=2, dim=1)
+scores = (embeddings[:2] @ embeddings[2:].T) * 100
+print(scores.tolist())
+# [[69.5, 30.5, 26.0],
+# [32.25, 66.5, 30.25]]
+```
+---