Update app.py

app.py

@@ -1,8 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 from transformers import AutoTokenizer, AutoModelForCausalLM
-import os
-os.environ["KERAS_BACKEND"] = "jax"
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
@@ -39,11 +37,13 @@ body::before {
 
 """
 
-model_id = "harishnair04/Gemma-medtr-2b-sft-v2-gguf"
-filename = "Gemma-medtr-2b-sft-v2.gguf"
+model_id = "harishnair04/Gemma-medtr-2b-sft-v2"
+# filename = "Gemma-medtr-2b-sft-v2.gguf"
 
-tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
-gemma_model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)
+# tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
+# gemma_model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+gemma_model = AutoModelForCausalLM.from_pretrained(model_id)
 
 tokenizer.pad_token_id = tokenizer.eos_token_id