From 0408925f0d316ddcec4288cc584604652c64dff6 Mon Sep 17 00:00:00 2001
From: Matthias Neumayer <hello@matthiasneumayer.com>
Date: Wed, 12 Feb 2025 12:14:50 +0100
Subject: [PATCH] Update README.md to include how to set temperature

---
 llms/README.md | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/llms/README.md b/llms/README.md
index 4f7451c1..3c5a0b3d 100644
--- a/llms/README.md
+++ b/llms/README.md
@@ -64,6 +64,29 @@ prompt = tokenizer.apply_chat_template(
 text = generate(model, tokenizer, prompt=prompt, verbose=True)
 ```
 
+To use temperature or other sampler arguments pass it like this
+
+```
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Mistral-7B-Instruct-v0.3-4bit")
+
+temp: 0.7
+top_p: 0.9
+top_k: 25
+sampler = make_sampler(temp, top_p,top_k)
+
+prompt = "Write a story about Ada Lovelace"
+
+messages = [{"role": "user", "content": prompt}]
+prompt = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True
+)
+
+text = generate(model, tokenizer, prompt=prompt, sampler, verbose=True)
+
+```
+
 To see a description of all the arguments you can do:
 
 ```