From 11a2daebf3ab9ed9f8d0d96c24a7d7e95456e653 Mon Sep 17 00:00:00 2001
From: Awni Hannun <awni@apple.com>
Date: Sat, 7 Sep 2024 08:23:49 -0700
Subject: [PATCH] fix bug in upload + docs nit

---
 llms/mlx_lm/LORA.md  | 30 +++++++-----------------------
 llms/mlx_lm/utils.py |  2 +-
 2 files changed, 8 insertions(+), 24 deletions(-)

diff --git a/llms/mlx_lm/LORA.md b/llms/mlx_lm/LORA.md
index 2e739d0f..3bf1ac68 100644
--- a/llms/mlx_lm/LORA.md
+++ b/llms/mlx_lm/LORA.md
@@ -166,44 +166,28 @@ Currently, `*.jsonl` files support three data formats: `chat`,
 `chat`:
 
 ```jsonl
-{
-  "messages": [
-    {
-      "role": "system",
-      "content": "You are a helpful assistant."
-    },
-    {
-      "role": "user",
-      "content": "Hello."
-    },
-    {
-      "role": "assistant",
-      "content": "How can I assistant you today."
-    }
-  ]
-}
+{"messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Hello." }, { "role": "assistant", "content": "How can I assistant you today." } ] }
 ```
 
 `completions`:
 
 ```jsonl
-{
-  "prompt": "What is the capital of France?",
-  "completion": "Paris."
-}
+{"prompt": "What is the capital of France?", "completion": "Paris."}
 ```
 
 `text`:
 
 ```jsonl
-{
-  "text": "This is an example for the model."
-}
+{"text": "This is an example for the model."}
 ```
 
 Note, the format is automatically determined by the dataset. Note also, keys in
 each line not expected by the loader will be ignored.
 
+> [!NOTE]
+> Each example in the datasets must be on a single line. Do not put more than
+> one example per line and do not split an example accross multiple lines.
+
 ### Hugging Face Datasets
 
 To use Hugging Face datasets, first install the `datasets` package:
diff --git a/llms/mlx_lm/utils.py b/llms/mlx_lm/utils.py
index ad9b3221..b4a2ea51 100644
--- a/llms/mlx_lm/utils.py
+++ b/llms/mlx_lm/utils.py
@@ -581,7 +581,7 @@ def upload_to_hub(path: str, upload_repo: str, hf_path: str):
         prompt="hello"
 
         if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
-            messages = [{"role": "user", "content": prompt}]
+            messages = [{{"role": "user", "content": prompt}}]
             prompt = tokenizer.apply_chat_template(
                 messages, tokenize=False, add_generation_prompt=True
             )