update per PR feedback to handle deprecated sharegpt types

requirements.txt

@@ -32,4 +32,4 @@ scikit-learn==1.2.2
 pynvml
 art
 wandb
-fschat
+fschat==0.2.29

src/axolotl/utils/config.py

@@ -262,6 +262,25 @@ def validate_config(cfg):
                     "`model_type: MixFormerSequentialForCausalLM` required for sample_packing"
                 )
 
+    if cfg.datasets:
+        for idx, ds_cfg in enumerate(cfg.datasets):
+            if ds_cfg.type == "sharegpt:chat":
+                LOG.warning(
+                    PendingDeprecationWarning(
+                        "`type: sharegpt:chat` will soon be deprecated. simply use `type: sharegpt` instead."
+                    )
+                )
+                cfg.datasets[idx].type = "sharegpt"
+            if "sharegpt_simple" in ds_cfg.type:
+                LOG.warning(
+                    PendingDeprecationWarning(
+                        "`type: sharegpt_simple` will soon be deprecated. simply use `type: sharegpt` instead."
+                    )
+                )
+                cfg.datasets[idx].type = cfg.datasets[idx].type.replace(
+                    "sharegpt_simple", "sharegpt"
+                )
+
     # TODO
     # MPT 7b
     # https://github.com/facebookresearch/bitsandbytes/issues/25

tests/test_validation.py

@@ -351,3 +351,26 @@ def test_packing(self):
         regex_exp = r".*set only one of max_packed_sequence_len \(deprecated soon\) or sample_packing.*"
         with pytest.raises(ValueError, match=regex_exp):
             validate_config(cfg)
+
+    def test_sharegpt_deprecation(self):
+        cfg = DictDefault(
+            {"datasets": [{"path": "lorem/ipsum", "type": "sharegpt:chat"}]}
+        )
+        with self._caplog.at_level(logging.WARNING):
+            validate_config(cfg)
+            assert any(
+                "`type: sharegpt:chat` will soon be deprecated." in record.message
+                for record in self._caplog.records
+            )
+        assert cfg.datasets[0].type == "sharegpt"
+
+        cfg = DictDefault(
+            {"datasets": [{"path": "lorem/ipsum", "type": "sharegpt_simple:load_role"}]}
+        )
+        with self._caplog.at_level(logging.WARNING):
+            validate_config(cfg)
+            assert any(
+                "`type: sharegpt_simple` will soon be deprecated." in record.message
+                for record in self._caplog.records
+            )
+        assert cfg.datasets[0].type == "sharegpt:load_role"