Update README.md

README.md

@@ -6,6 +6,15 @@ pipeline_tag: text-generation
 inference: false
 library_name: transformers
 ---
+# ⚠️ DEPRECATION WARNING ⚠️
+
+This model is an outdated version and has been preserved specifically for evaluating differences between model versions. 
+
+We highly recommend visiting our GitHub repository to find and use the latest version of the model: https://github.com/OpenBuddy/OpenBuddy
+
+
+
+
 # OpenBuddy - Open Multilingual Chatbot based on LLaMA
 
 GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
@@ -22,20 +31,6 @@ Due to licensing restrictions from LLAMA, you need to have the original LLAMA-7B
 python(3) decrypt.py [path-to-consolidated.00.pth] [path-to-our-model-folder]
 ```
 
-## Usage
-
-OpenBuddy is a model that uses `bf16` format. However, some libraries or frameworks may tend to default to fp16 format conversion and loading, which can cause unexpected results in the model. 
-
-If you are using the Transformers library, you can load the model in the following way:
-
-```Python
-MODEL_PATH = './openbuddy-7b-bf16-enc'
-model = LlamaForCausalLM.from_pretrained(model_path, torch_dtype=torch.bfloat16) 
-tokenizer = LlamaTokenizer.from_pretrained(model_path)
-```
-
-Here, the torch_dtype argument is set to torch.bfloat16 to ensure that the model is loaded in bf16 format.
-
 ## Disclaimer
 
 OpenBuddy is provided as-is without any warranty of any kind, either express or implied. The authors and contributors shall not be held liable for any damages resulting from the use or inability to use this software. By using OpenBuddy, you agree to these terms and conditions.