diff --git a/laya/agent.py b/laya/agent.py
index 70163bf..b7b9a0b 100644
--- a/laya/agent.py
+++ b/laya/agent.py
@@ -186,7 +186,8 @@ class Agent:
                 self.device = torch.device("cpu")
 
         tok_dir = os.path.join(model_dir, "tokenizer")
-        self.tok = AutoTokenizer.from_pretrained(tok_dir if os.path.exists(tok_dir) else self.cfg.get("encoder"))
+        self.tok = AutoTokenizer.from_pretrained(tok_dir if os.path.exists(tok_dir) else self.cfg.get("encoder"),
+                                                 trust_remote_code=bool(self.cfg.get("trust_remote_code", False)))
 
         enc_dir = os.path.join(model_dir, "encoder")
         # The checkpoint supplies every parameter; skip random/base-model weights.
diff --git a/laya/common.py b/laya/common.py
index 950c41d..6a633f7 100644
--- a/laya/common.py
+++ b/laya/common.py
@@ -139,11 +139,25 @@ class DecisionModel(nn.Module):
 def build_model(cfg: Dict, encoder_dir: Optional[str] = None, pretrained: bool = True) -> DecisionModel:
     from transformers import AutoConfig, AutoModel
 
+    # Encoders whose modeling code lives on the Hub (e.g. NeoBERT) must opt in via the config.
+    remote = bool(cfg.get("trust_remote_code", False))
     if not pretrained or (encoder_dir and os.path.exists(encoder_dir)):
-        ecfg = AutoConfig.from_pretrained(encoder_dir or cfg["encoder"])
-        enc = AutoModel.from_config(ecfg, attn_implementation="sdpa")
+        ecfg = AutoConfig.from_pretrained(encoder_dir or cfg["encoder"], trust_remote_code=remote)
+        enc = AutoModel.from_config(ecfg, attn_implementation="sdpa", trust_remote_code=remote)
     else:
-        enc = AutoModel.from_pretrained(cfg["encoder"], attn_implementation="sdpa")
+        enc = AutoModel.from_pretrained(cfg["encoder"], attn_implementation="sdpa", trust_remote_code=remote)
+    # NeoBERT computes its RoPE tables as non-persistent buffers in __init__; transformers 5 builds models on
+    # the meta device, so they come back as uninitialised memory and every forward pass returns NaN.
+    if hasattr(enc, "freqs_cos"):
+        import sys
+
+        precompute = sys.modules[type(enc).__module__].precompute_freqs
+        c = enc.config
+        enc.freqs_cos, enc.freqs_sin = precompute(c.hidden_size // c.num_attention_heads, c.max_length)
+    # Some encoder configs pin a half-precision dtype (NeoBERT ships bfloat16), which transformers 5 honours. Keep
+    # master weights in float32: bf16 weights round most optimizer updates to zero, and CPU inference in bf16 is ~8x slower.
+    # Mixed precision is applied by autocast at train/inference time instead.
+    enc = enc.float()
     return DecisionModel(enc, cfg.get("head_layers", 2), len(cfg.get("act_costs", {})) + 1)