Update README.md

README.md

@@ -39,9 +39,30 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
 ### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
+"""
+from unsloth import FastLanguageModel
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "huyremy/aichat", # YOUR MODEL YOU USED FOR TRAINING
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+)
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+
+# alpaca_prompt = You MUST copy from above!
+
+inputs = tokenizer(
+[
+    alpaca_prompt.format(
+        "who is Nguyễn Phú Trọng?", # instruction
+        "", # input
+        "", # output - leave this blank for generation!
+    ),
+], return_tensors = "pt").to("cuda")
+
+outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
+tokenizer.batch_decode(outputs)
+""
 [More Information Needed]
 
 ### Downstream Use [optional]