diff --git a/llama2_c/README.md b/llama2_c/README.md
index ac21795..8b3d0ee 100644
--- a/llama2_c/README.md
+++ b/llama2_c/README.md
@@ -149,6 +149,7 @@ For quick tests, we have included a really small model, with only 260K parameter
 
 The CI/CD using a GitHub actions workflow, and the demo_pytest.sh script are based on this model.
 
+
 # demo_pytest.sh
 
 - The demo_pytest.sh script starts the local network, deploys llama2_260K, uploads the model & tokenizer, and runs the QA with pytest:
@@ -161,25 +162,15 @@ The CI/CD using a GitHub actions workflow, and the demo_pytest.sh script are bas
   - `./demo.sh` , on Linux / Mac
   - `.\demo.ps1` , in Windows PowerShell (Miniconda recommended)
 
-# More models
+# Models
 
-- You can get other model checkpoints, as explained in [karpathy/llama2.c](https://github.com/karpathy/llama2.c):
+## HuggingFace
 
-  This command downloads the 15M parameter model that was trained on the TinyStories dataset (~60MB download) and stores it in a `models` folder:
+You can find many models in the llama2_c *.bin format on HuggingFace, for example:
 
-  ```bash
-  # on Linux/Mac
-  mkdir -p models
-  wget -P models https://huggingface.co/karpathy/tinyllamas/resolve/main/stories15M.bin
-  ```
+- [onicai/llama2_c_canister_models](https://huggingface.co/onicai/llama2_c_canister_models)
+- [karpathy/tinyllamas](https://huggingface.co/karpathy/tinyllamas)
 
-  ```powershell
-  # in Windows PowerShell (Miniconda recommended)
-  if (-not (Test-Path -Path .\models)) {
-   New-Item -Path .\models -ItemType Directory
-  }
-  Invoke-WebRequest -Uri https://huggingface.co/karpathy/tinyllamas/resolve/main/stories15M.bin -OutFile .\models\stories15M.bin
-  ```
 
 # Deploying to the IC main net
 
diff --git a/llama2_c/scripts/nft_update_story.py b/llama2_c/scripts/nft_update_story.py
index aef3d78..499c3e0 100644
--- a/llama2_c/scripts/nft_update_story.py
+++ b/llama2_c/scripts/nft_update_story.py
@@ -156,12 +156,14 @@ def main() -> int:
         print(response)
         if "Ok" in response[0].keys():
             # Check if the number of generated tokens is less than the requested tokens
-            if response[0]["Ok"]["num_tokens"] < prompt['steps']:
+            if response[0]["Ok"]["num_tokens"] < prompt["steps"]:
                 print(f'The end! - num_tokens = {response[0]["Ok"]["num_tokens"]}')
                 break
             # Check if the response is an empty string. If it is, break out of the loop.
             if response[0]["Ok"]["inference"] == "":
-                print("The end! - we got an empty string. THIS IS AN ERROR ACTUALLY. WE SHOULD NOT GET HERE..")
+                print(
+                    "The end! - we got an empty string. (ERROR: WE SHOULD NOT GET HERE)"
+                )
                 print("Something went wrong:")
                 sys.exit(1)
         else: