wip

Signed-off-by: Raphael Glon <[email protected]>

app.py

@@ -45,7 +45,7 @@ def _ensure_loaded():
     _model = AutoModelForCausalLM.from_pretrained(
         MODEL_ID,
         trust_remote_code=True,
-        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+        # torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
         low_cpu_mem_usage=True,
         device_map="auto" if torch.cuda.is_available() else None,
     )