Update README.md

Improve model card with usage and evaluation notes

README.md

@@ -112,4 +112,25 @@ model = PeftModel.from_pretrained(
     adapter_id
 )
 
-model.eval()
+model.eval()
+
+Load the tokenizer from the base model because it contains the correct
+Qwen chat template.
+
+Model repository
+
+Hugging Face:
+
+mgbam/gaialab-naija-adapter-v0.1
+
+Source code
+
+GitHub:
+
+oluwafemidiakhoa/gaialab-naija-assistant
+
+Disclaimer
+
+This is an experimental research release. Generated responses should be
+reviewed before use in business, legal, financial, tax, medical, or
+regulatory contexts.