Set config.use_mem_rope to True

config.json

@@ -12,6 +12,7 @@
   "conv_kernel": 3,
   "d_model": 16,
   "d_state": 32,
+  "dtype": "float32",
   "eos_token_id": 2,
   "expand": 2,
   "hidden_act": "gelu",
@@ -44,18 +45,21 @@
   "num_query_groups": 32,
   "pad_token_id": 0,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 10000,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
   "time_step_floor": 0.0001,
   "time_step_limit": null,
   "time_step_max": 0.1,
   "time_step_min": 0.001,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.4",
+  "transformers_version": "5.0.0",
   "use_cache": true,
   "use_conv_bias": true,
   "use_long_context": false,
   "use_mem_eff_path": false,
-  "use_mem_rope": false,
+  "use_mem_rope": true,
   "use_shared_attention_adapter": false,
   "vocab_size": 50280
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.55.4"
+  "transformers_version": "5.0.0"
 }

pytorch_model.bin → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa28ee93e29e40c5fc35e5727122220d5dc937b65f27f71995c8edbb056e551c
-size 3408858
+oid sha256:257244fe95a815ccdfc00b230826eb464c8b6bfc791d6e8c35ec7a0e470ae4fb
+size 3398168