Update README.md

README.md

@@ -11,7 +11,6 @@ datasets:
 - andersonbcdefg/supernatural-instructions-2m
 - HuggingFaceH4/ultrachat_200k
 - HuggingFaceH4/ultrafeedback_binarized
-- mlabonne/orpo-dpo-mix-40k
 language:
 - en
 - it
@@ -245,7 +244,7 @@ wants to provide Italian NLP researchers with an improved model the for Italian
 ## Specifications
 
 - **Model developers**: Ph.D. Marco Polignano - University of Bari Aldo Moro, Italy
-- **Variations**: The model release has been **supervised fine-tuning (SFT)** using **QLoRA** in the 4bit version, on a long list of instruction-based datasets. **ORPO** approach over the *mlabonne/orpo-dpo-mix-40k* dataset is used to align with human preferences for helpfulness and safety.
+- **Variations**: The model release has been **supervised fine-tuning (SFT)** using **QLoRA**, on a long list of instruction-based datasets. **DPO** approach over the *HuggingFaceH4/ultrafeedback_binarized* dataset is used to align with human preferences for helpfulness and safety.
 - **Input**: Models input text only.
 - **Output**: Models generate text and code only.
 - **Model Architecture**: *Llama 3 architecture*.
@@ -276,7 +275,7 @@ For direct use with `transformers`, you can easily get started with the followin
       AutoTokenizer,
   )
 
-  base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-sft-ORPO"
+  base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-sft-DPO"
   model = AutoModelForCausalLM.from_pretrained(
       base_model,
       torch_dtype=torch.bfloat16,
@@ -307,7 +306,7 @@ For direct use with `transformers`, you can easily get started with the followin
       BitsAndBytesConfig,
   )
 
-  base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-sft-ORPO"
+  base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-sft-DPO"
   bnb_config = BitsAndBytesConfig(
       load_in_4bit=True,
       bnb_4bit_quant_type="nf4",
@@ -350,7 +349,7 @@ For direct use with `unsloth`, you can easily get started with the following ste
   from unsloth import FastLanguageModel
   import torch
 
-  base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-sft-ORPO"
+  base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-sft-DPO"
   model, tokenizer = FastLanguageModel.from_pretrained(
       model_name = base_model,
       max_seq_length = 8192,