Upload 3 files

requirements.txt

@@ -0,0 +1,4 @@
+transformers==4.28.1
+datasets==2.12.0
+accelerate==0.21.0
+torch==2.0.1

train_phi3.py

@@ -0,0 +1,12 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments
+from datasets import load_dataset
+
+# Load model and tokenizer
+model_name = "microsoft/Phi-3-mini-128k-instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Load dataset
+dataset = load_dataset("text", data_files="combined_tokenized_data.txt")["train"]
+
+# ... (rest of your code for tokenization, data collator, training arguments, etc.)