Add explicit error for flash + alibi

mosaic_gpt.py

@@ -31,6 +31,9 @@ class MosaicGPT(PreTrainedModel):
     def __init__(self, config: MosaicGPTConfig):
         super().__init__(config)
 
+        if config.attn_impl == 'flash' and config.alibi:
+            raise RuntimeError("ALiBi is not supported with flash attention. Please use triton or torch.")
+
         self.attn_impl = config.attn_impl
         self.prefix_lm = config.prefix_lm
         self.attn_uses_sequence_id = config.attn_uses_sequence_id