Update README.md

README.md

@@ -15,6 +15,25 @@ A lightweight model (2.8B) with enhanced RAG capabilities, with lower risk of ha
 
 This is a DPO fine-tune of the Phi-2 architecture (in particular, dolphin-2_6-phi-2) over the dataset https://huggingface.co/datasets/jondurbin/contextual-dpo-v0.1.
 
+## Usage
+
+Load the model as
+
+```
+model = AutoModelForCausalLM.from_pretrained(
+    "vicgalle/phi-2-contextual",
+    torch_dtype="auto",
+    load_in_4bit=True,
+    trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained(
+    "cognitivecomputations/dolphin-2_6-phi-2",
+    trust_remote_code=True
+)
+```
+
+and use the following prompt template.
+
 
 ## Prompt format