Update README.md

README.md

@@ -1,29 +1,32 @@
 ---
 base_model: google/gemma-2-2b-it
 library_name: peft
+license: apache-2.0
+language:
+- es
+tags:
+- news
+- chat
+- LoRa
+- conversational AI
 ---
 
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-
+Lightweight finetuning of google/gemma-2-2b-it on a public dataset of news from Spanish digital newspapers (https://www.kaggle.com/datasets/josemamuiz/noticias-laraznpblico/).
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-
+This model is fine-tuned using LoRa (Low-Rank Adaptation) on the "Noticias La Razón y Público" dataset, a collection of Spanish news articles. The finetuning was done with lightweight methods to ensure efficient training while maintaining performance on the news-related language generation tasks.
 
-- **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]
+- **Developed by:** https://talkingtochatbots.com
+- **Language(s) (NLP):** Spanish (es)
+- **License:** apache-2.0
+- **Finetuned from model:** google/gemma-2-2b-it
 
 ### Model Sources [optional]
 
@@ -39,9 +42,7 @@ library_name: peft
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
+This model can be used for **conversational AI tasks** related to Spanish-language news. The fine-tuned LoRa model is especially suitable for use cases that require both understanding and generating text, such as chat-based interactions, answering questions about news, and discussing headlines.
 
 ### Downstream Use [optional]
 
@@ -71,7 +72,21 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+# Load the tokenizer and model
+save_directory = "./fine_tuned_model"
+tokenizer = AutoTokenizer.from_pretrained(save_directory)
+model = AutoModelForCausalLM.from_pretrained(save_directory)
+peft_model = PeftModel.from_pretrained(model, save_directory)
+
+# Example usage
+input_text = "¿Qué opinas de las noticias recientes sobre la economía?"
+inputs = tokenizer(input_text, return_tensors="pt")
+output = peft_model.generate(**inputs, max_length=50)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 
 ## Training Details