Update for vllm

config.json

@@ -20,12 +20,16 @@
   "pad_token_id": 3,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.30.1",
   "use_cache": true,
   "use_stable_embedding": true,
-  "vocab_size": 100096
+  "vocab_size": 100096,
+  "rope_scaling": {
+    "type": "ntkmixed",
+    "factor": 16.0,
+    "power": 0.3
+  }
 }

configuration_bluelm.py

@@ -149,14 +149,14 @@ class BlueLMConfig(PretrainedConfig):
         if self.rope_scaling is None:
             return
 
-        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
             raise ValueError(
-                "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
+                "`rope_scaling` must be a dictionary with with three fields, `type` , `factor` , `power`, "
                 f"got {self.rope_scaling}"
             )
         rope_scaling_type = self.rope_scaling.get("type", None)
         rope_scaling_factor = self.rope_scaling.get("factor", None)
-        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
+        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic","ntkmixed"]:
             raise ValueError(
                 f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
             )