update README with docs on exo run command

4443d3ce9ac507c2d3fa48a239d3198f9478f92b · 2024-10-02 16:39:19 +0400 · Alex Cheema

Files touched

M README.md

Diff

commit 4443d3ce9ac507c2d3fa48a239d3198f9478f92b
Author: Alex Cheema <alexcheema123@gmail.com>
Date:   Wed Oct 2 16:39:19 2024 +0400

    update README with docs on exo run command
---
 README.md | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index d729e16e..f8430e5d 100644
--- a/README.md
+++ b/README.md
@@ -130,13 +130,13 @@ exo starts a ChatGPT-like WebUI (powered by [tinygrad tinychat](https://github.c
 
 For developers, exo also starts a ChatGPT-compatible API endpoint on http://localhost:8000/v1/chat/completions. Examples with curl:
 
-#### Llama 3.1 8B:
+#### Llama 3.2 3B:
 
 ```sh
 curl http://localhost:8000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-     "model": "llama-3.1-8b",
+     "model": "llama-3.2-3b",
      "messages": [{"role": "user", "content": "What is the meaning of exo?"}],
      "temperature": 0.7
    }'
@@ -201,6 +201,17 @@ Linux devices will automatically default to using the **tinygrad** inference eng
 
 You can read about tinygrad-specific env vars [here](https://docs.tinygrad.org/env_vars/). For example, you can configure tinygrad to use the cpu by specifying `CLANG=1`.
 
+### Example Usage on a single device with "exo run" command
+
+```sh
+exo run llama-3.2-3b
+```
+
+With a custom prompt:
+
+```sh
+exo run llama-3.2-3b --prompt "What is the meaning of exo?"
+```
 
 ## Debugging

← 8ae59b70 add exo run command. usage: exo run <model-name> e.g. exo ru · back to Exo · remove hf-transfer, huggingface-hub, Jinja2 unused dependenc 413ecb1b →