Apply quant method

app.py

@@ -21,6 +21,12 @@ from mlx_lm import convert
 
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
+# I'm not sure if we need to add more stuff here
+QUANT_PARAMS = {
+    "Q4": 4,
+    "Q8": 8,
+}
+
 def clear_hf_cache_space():
     scan = scan_cache_dir()
     to_delete = []
@@ -83,17 +89,14 @@ def process_model(model_id, q_method, oauth_token: gr.OAuthToken | None):
         raise ValueError("You must be logged in to use MLX-my-repo")
     
     model_name = model_id.split('/')[-1]
-    print(model_name)
     username = whoami(oauth_token.token)["name"]
-    print(username)
-    
     try:
-        upload_repo = username + "/" + model_name + "-mlx"
+        upload_repo = f"{username}/{model_name}-{q_method}-mlx"
         print(upload_repo)
         with tempfile.TemporaryDirectory(dir="converted") as tmpdir:
             # The target dir must not exist
             mlx_path = os.path.join(tmpdir, "mlx")
-            convert(model_id, mlx_path=mlx_path, quantize=True)
+            convert(model_id, mlx_path=mlx_path, quantize=True, q_bits=QUANT_PARAMS[q_method])
             print("Conversion done")
             upload_to_hub(path=mlx_path, upload_repo=upload_repo, hf_path=model_id, token=oauth_token.token)
             print("Upload done")