Update app.py

app.py

@@ -103,6 +103,15 @@ tokenizer.save_pretrained("./llama-2-7b-chat_fine_tuned")
 model.push_to_hub("jonACE/llama-2-7b-chat_fine_tuned", token=hf_token)
 tokenizer.push_to_hub("jonACE/llama-2-7b-chat_fine_tuned", token=hf_token)
 
+# save GGUF versions
+model.save_pretrained_gguf("./llama-2-7b-chat_fine_tuned", tokenizer,)
+model.push_to_hub_gguf("jonACE/llama-2-7b-chat_fine_tuned", tokenizer)
+
+model.save_pretrained_gguf("./llama-2-7b-chat_fine_tuned", tokenizer, quantization_method = "f16")
+model.push_to_hub_gguf("jonACE/llama-2-7b-chat_fine_tuned", tokenizer, quantization_method = "f16")
+
+model.save_pretrained_gguf("./llama-2-7b-chat_fine_tuned", tokenizer, quantization_method = "q4_k_m")
+model.push_to_hub_gguf("jonACE/llama-2-7b-chat_fine_tuned", tokenizer, quantization_method = "q4_k_m")
 
 # CHATBOT START
 # chatbot = pipeline("text-generation", model="jonACE/llama-2-7b-chat_fine_tuned")