From 4aae8a678cae377ce5b98f7df9948db15b2e282f Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Wed, 21 Feb 2024 03:58:03 +1100
Subject: [PATCH] Updated Home (markdown)

---
 Home.md | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/Home.md b/Home.md
index 8b534e9..9df827a 100644
--- a/Home.md
+++ b/Home.md
@@ -167,6 +167,21 @@ tokenizer = get_chat_template(
 )
 ```
 
+### 2x Faster Inference
+Unsloth supports natively 2x faster inference. All QLoRA, LoRA and non LoRA inference paths are 2x faster. This requires no change of code or any new dependencies.
+```python
+from unsloth import FastLanguageModel
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "lora_model", # 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
+text_streamer = TextStreamer(tokenizer)
+_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 64)
+```
+
 ### NotImplementedError: A UTF-8 locale is required. Got ANSI
 See https://github.com/googlecolab/colabtools/issues/3409