From 966c5d4bda09ce9c564197f460d316c616079e86 Mon Sep 17 00:00:00 2001
From: Aarav Navani <arav.navani@gmail.com>
Date: Thu, 29 Aug 2024 12:58:06 -0700
Subject: [PATCH] lintg

---
 inference/download_model.py                | 3 +--
 inference/serving-non-optimized-fastapi.py | 3 ---
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/inference/download_model.py b/inference/download_model.py
index e8443e1..5ffee0e 100644
--- a/inference/download_model.py
+++ b/inference/download_model.py
@@ -37,8 +37,7 @@
 )
 def download_model(model_name, model_revision, force_download=False):
     from huggingface_hub import snapshot_download
-    from transformers import AutoTokenizer, AutoModelForCausalLM
-    import json
+    from transformers import AutoTokenizer
     import os
 
     volume.reload()
diff --git a/inference/serving-non-optimized-fastapi.py b/inference/serving-non-optimized-fastapi.py
index 0c55876..1c69be8 100644
--- a/inference/serving-non-optimized-fastapi.py
+++ b/inference/serving-non-optimized-fastapi.py
@@ -53,9 +53,6 @@ def load(self):
 
     @modal.method()
     def generate(self, chat):
-        import torch
-        from torch.nn.functional import softmax
-
         tokenizer = self.tokenizer
         model = self.model