Update README.md

README.md

@@ -15,7 +15,7 @@ tags:
 
 XXXX is an updated version of [Mistral-7B-v0.2](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf), specifically fine-tuned with SFT and LoRA adjustments.
 
-- It's trained both on publicly available datasets, like [SQUAD-it](https://huggingface.co/datasets/squad_it), and datasets we've created in-house.
+- It's trained on publicly available datasets, like [SQUAD-it](https://huggingface.co/datasets/squad_it), and datasets we've created in-house.
 - it's designed to understand and maintain context, making it ideal for Retrieval Augmented Generation (RAG) tasks and applications requiring contextual awareness.
 
 # Evaluation
@@ -29,26 +29,22 @@ We evaluated the model using the same test sets as used for the Open Ita LLM Lea
 
 ## Usage
 
-Be sure to have transformers, peft and sentencepiece installed
+Be sure to have transformers and torch installed
 
 ```python
-pip install transformers peft sentencepiece
+pip install transformers torch
 ```
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel, PeftConfig
 
-device = "cuda"
+device = "cuda" # change to cpu if you have no gpu
 
-config = PeftConfig.from_pretrained("MoxoffSpA/xxxx")
-model = AutoModelForCausalLM.from_pretrained("alpindale/Mistral-7B-v0.2-hf")
-tokenizer = AutoTokenizer.from_pretrained("alpindale/Mistral-7B-v0.2-hf")
-
-model = PeftModel.from_pretrained(model, "MoxoffSpA/xxxx")
+model = AutoModelForCausalLM.from_pretrained("MoxoffSpA/xxxx")
+tokenizer = AutoTokenizer.from_pretrained("MoxoffSpA/xxxx")
 
 messages = [
-    {"role": "user", "content": "Qual è il tuo piatto preferito??"},
+    {"role": "user", "content": "Qual è il tuo piatto preferito?"},
     {"role": "assistant", "content": "Beh, ho un debole per una buona porzione di risotto allo zafferano. È un piatto che si distingue per il suo sapore ricco e il suo bellissimo colore dorato, rendendolo irresistibile!"},
     {"role": "user", "content": "Hai delle ricette con il risotto che consigli?"}
 ]
@@ -58,7 +54,7 @@ encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
 model_inputs = encodeds.to(device)
 model.to(device)
 
-generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
+generated_ids = model.generate(model_inputs, max_new_tokens=250, do_sample=True)
 decoded = tokenizer.batch_decode(generated_ids)
 print(decoded[0])
 ```