diff --git a/modules/llamacpp_hf.py b/modules/llamacpp_hf.py
index 5d05f5df..94d893c4 100644
--- a/modules/llamacpp_hf.py
+++ b/modules/llamacpp_hf.py
@@ -97,6 +97,8 @@ class LlamacppHF(PreTrainedModel):
             'use_mlock': shared.args.mlock,
             'low_vram': shared.args.low_vram,
             'n_gpu_layers': shared.args.n_gpu_layers,
+            'rope_freq_base': 10000 * shared.args.alpha_value ** (64/63.),
+            'rope_freq_scale': 1.0 / shared.args.compress_pos_emb,
             'logits_all': True,
         }
 
diff --git a/modules/llamacpp_model.py b/modules/llamacpp_model.py
index 86537a27..180b0f37 100644
--- a/modules/llamacpp_model.py
+++ b/modules/llamacpp_model.py
@@ -50,7 +50,9 @@ class LlamaCppModel:
             'use_mmap': not shared.args.no_mmap,
             'use_mlock': shared.args.mlock,
             'low_vram': shared.args.low_vram,
-            'n_gpu_layers': shared.args.n_gpu_layers
+            'n_gpu_layers': shared.args.n_gpu_layers,
+            'rope_freq_base': 10000 * shared.args.alpha_value ** (64/63.),
+            'rope_freq_scale': 1.0 / shared.args.compress_pos_emb,
         }
 
         result.model = Llama(**params)
diff --git a/modules/loaders.py b/modules/loaders.py
index da38c2f5..b760128f 100644
--- a/modules/loaders.py
+++ b/modules/loaders.py
@@ -37,6 +37,8 @@ loaders_and_params = {
         'low_vram',
         'mlock',
         'llama_cpp_seed',
+        'compress_pos_emb',
+        'alpha_value',
     ],
     'llamacpp_HF': [
         'n_ctx',
@@ -47,6 +49,8 @@ loaders_and_params = {
         'low_vram',
         'mlock',
         'llama_cpp_seed',
+        'compress_pos_emb',
+        'alpha_value',
         'llamacpp_HF_info',
     ],
     'Transformers': [