Update README.md

README.md

@@ -10,23 +10,163 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# aguila-es-inclusivo-adapters_v3
 
-This model is a fine-tuned version of [projecte-aina/aguila-7b](https://huggingface.co/projecte-aina/aguila-7b) on an unknown dataset.
+
+
+
+# es-inclusivo-translator
+
+This model is a fine-tuned version of [projecte-aina/aguila-7b](https://huggingface.co/projecte-aina/aguila-7b) on the dataset [somosnlp/es-inclusive-language](https://huggingface.co/datasets/somosnlp/es-inclusive-language).
+
+Languages are powerful tools to communicate ideas, but their use is not impartial. The selection of words carries inherent biases and reflects subjective perspectives. In some cases, language is wielded to enforce ideologies, marginalize certain groups, or promote specific political agendas.
+Spanish is not the exception to that. For instance, when we say “los alumnos” or “los ingenieros”, we are excluding women from those groups. Similarly, expressions such as “los gitanos” o “los musulmanes” perpetuate discrimination against these communities.
+
+In response to these linguistic challenges, this model offers a way to construct inclusive alternatives in accordance with official guidelines on inclusive language from various Spanish speaking countries. Its purpose is to provide grammatically correct and inclusive solutions to situations where our language choices might otherwise be exclusive. 
+This is a tool that contributes to the fifth of the Sustainable Development Goals: Achieve gender equality and empower all women and girls.
+
+The model works in such a way that, given an input text, it returns the original text rewritten using inclusive language.
+
 It achieves the following results on the evaluation set:
-- Loss: 0.6292
+- Loss: 0.6030
 
 ## Model description
+- **Developed by**: [Andrés Martínez Fernández-Salguero](https://huggingface.co/Andresmfs) (andresmfs), Imanuel Rozenberg (manu_20392), Gaia Quintana Fleitas (gaiaq), Josué Sauca (josue_sauca), Miguel López (wizmik12)
+- **Language(s)**: Spanish
+- **Fine-tuned from the model**: [projecte-aina/aguila-7b](https://huggingface.co/projecte-aina/aguila-7b)
+- **Licence**: cc-by-nc-sa-4.0
 
-More information needed
+## Social Impact
+An inclusive translator holds significant social impact by promoting equity and representation within texts. By rectifying biases ingrained in language and fostering inclusivity, it combats discrimination, amplifies the visibility of marginalized groups, and contributes  to the cultivation of a more inclusive and respectful society.
+This is a tool that contributes to the fifth of the Sustainable Development Goals: Achieve gender equality and empower all women and girls.
 
 ## Intended uses & limitations
 
 More information needed
 
+### How to use
+Here is how to use this model:
+~~~
+from transformers import AutoTokenizer
+from transformers import AutoModelForCausalLM
+import torch
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained('somosnlp/', trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained('somosnlp/', trust_remote_code=True,
+    quantization_config=bnb_config,
+    device_map="auto")
+
+# generation_config
+generation_config = model.generation_config
+generation_config.max_new_tokens = 100
+generation_config.temperature = 0.7
+generation_config.top_p = 0.7
+generation_config.num_return_sequences = 1
+generation_config.pad_token_id = tokenizer.eos_token_id
+generation_config.eos_token_id = tokenizer.eos_token_id
+
+# Define inference function
+def translate_es_inclusivo(exclusive_text): 
+    
+    # generate input prompt
+    eval_prompt = f"""Reescribe el siguiente texto utilizando lenguaje inclusivo.\n
+      Texto: {exclusive_text}\n
+      Texto en lenguaje inclusivo:"""
+    
+    # tokenize input
+    model_input = tokenizer(eval_prompt, return_tensors="pt").to(model.device)
+    
+    # set max_new_tokens if necessary
+    if len(model_input['input_ids'][0]) > 80:
+        model.generation_config.max_new_tokens = len(model_input['input_ids'][0]) + 0.2 * len(model_input['input_ids'][0])
+    
+    # get length of encoded prompt
+    prompt_token_len = len(model_input['input_ids'][0])
+        
+    # generate and decode
+    with torch.no_grad():
+        inclusive_text = tokenizer.decode(model.generate(**model_input, generation_config=generation_config)[0][prompt_token_len:], 
+                                          skip_special_tokens=True)                                                                        
+    
+    return inclusive_text
+
+##########
+
+input_text = 'Los alumnos atienden a sus profesores'
+
+print(translate_es_inclusivo(input_text))
+~~~
+
+
+As it is a heavy model, you may want to use it in 4-bits:
+~~~
+from transformers import AutoTokenizer
+from transformers import AutoModelForCausalLM
+from transformers import BitsAndBytesConfig
+import torch
+
+
+## Load model in 4bits
+# bnb_configuration
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type='nf4',
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_use_double_quant=False)
+
+
+# model
+model = AutoModelForCausalLM.from_pretrained('somosnlp/', trust_remote_code=True,
+    quantization_config=bnb_config,
+    device_map="auto")
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained('somosnlp/', trust_remote_code=True)
+
+# generation_config
+generation_config = model.generation_config
+generation_config.max_new_tokens = 100
+generation_config.temperature = 0.7
+generation_config.top_p = 0.7
+generation_config.num_return_sequences = 1
+generation_config.pad_token_id = tokenizer.eos_token_id
+generation_config.eos_token_id = tokenizer.eos_token_id
+
+# Define inference function
+def translate_es_inclusivo(exclusive_text): 
+    
+    # generate input prompt
+    eval_prompt = f"""Reescribe el siguiente texto utilizando lenguaje inclusivo.\n
+      Texto: {exclusive_text}\n
+      Texto en lenguaje inclusivo:"""
+    
+    # tokenize input
+    model_input = tokenizer(eval_prompt, return_tensors="pt").to(model.device)
+    
+    # set max_new_tokens if necessary
+    if len(model_input['input_ids'][0]) > 80:
+        model.generation_config.max_new_tokens = len(model_input['input_ids'][0]) + 0.2 * len(model_input['input_ids'][0])
+    
+    # get length of encoded prompt
+    prompt_token_len = len(model_input['input_ids'][0])
+        
+    # generate and decode
+    with torch.no_grad():
+        inclusive_text = tokenizer.decode(model.generate(**model_input, generation_config=generation_config)[0][prompt_token_len:], 
+                                          skip_special_tokens=True)                                                                        
+    
+    return inclusive_text
+
+##########
+
+input_text = 'Los alumnos atienden a sus profesores'
+
+print(translate_es_inclusivo(input_text))
+~~~
+
 ## Training and evaluation data
 
-More information needed
+Training and evaluation data can be found in [somosnlp/es-inclusive-language](https://huggingface.co/datasets/somosnlp/es-inclusive-language)
 
 ## Training procedure
 
@@ -63,3 +203,4 @@ The following hyperparameters were used during training:
 - Pytorch 2.2.2+cu121
 - Datasets 2.18.0
 - Tokenizers 0.13.3
+