Update README.md

README.md

@@ -19,13 +19,13 @@ ItalIA is a LLM trained for the Italian language and based on Llama3-8b.
 
 ### Model Description
 
-ItalIA is a state-of-the-art language model specifically trained for the Italian language, leveraging the latest advancements in the LLM frameworks llama3. This model aims to provide highly accurate and context-aware natural language understanding and generation, making it ideal for a wide range of applications from automated customer support to content creation.
+ItalIA is a state-of-the-art language model specifically trained for the Italian language using unsloth, leveraging the latest advancements in the LLM frameworks llama3. This model aims to provide highly accurate and context-aware natural language understanding and generation, making it ideal for a wide range of applications from automated customer support to content creation.
 
 - **Developed by:** Davide Pizzo
-- **Model type:** [Transformer-based Large Language Model]
-- **Language(s) (NLP):** [Italian]
-- **License:** [Other]
-- **Finetuned from model [optional]:** [llama3-8b]
+- **Model type:** Transformer-based Large Language Model
+- **Language(s) (NLP):** Italian
+- **License:** Other
+- **Finetuned from model [optional]:** llama3-8b
 
 ### Model Sources [optional]
 
@@ -76,9 +76,9 @@ Users should be aware of the potential for biased outputs based on the training
 
 Use the code below to get started with the model.
 
-[from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "your-model-name-on-huggingface"
+model_name = "MethosPi/llama3-8b-italIA-unsloth-merged"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
@@ -86,7 +86,7 @@ text = "Inserisci qui il tuo testo in italiano."
 input_ids = tokenizer.encode(text, return_tensors="pt")
 output = model.generate(input_ids)
 
-print(tokenizer.decode(output[0], skip_special_tokens=True))]
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 
 ## Training Details