diff --git a/README.md b/README.md
index 1207763fc..028c2a817 100644
--- a/README.md
+++ b/README.md
@@ -117,6 +117,7 @@ Typically finetunes of the base models below are supported as well.
 - [x] [Mamba](https://github.com/state-spaces/mamba)
 - [x] [Xverse](https://huggingface.co/models?search=xverse)
 - [x] [Command-R](https://huggingface.co/CohereForAI/c4ai-command-r-v01)
+- [x] [SEA-LION](https://huggingface.co/models?search=sea-lion)
 
 **Multimodal models:**
 
diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py
index 3c15424e1..2cb8b79ca 100644
--- a/gguf-py/gguf/tensor_mapping.py
+++ b/gguf-py/gguf/tensor_mapping.py
@@ -289,13 +289,13 @@ class TensorNameMap:
         MODEL_TENSOR.ATTN_Q_NORM: (
             "language_model.encoder.layers.{bid}.self_attention.q_layernorm",
             "model.layers.{bid}.self_attn.q_layernorm",                       # persimmon
-            "transformer.blocks.{bid}.attn.q_ln",
+            "transformer.blocks.{bid}.attn.q_ln",                             # sea-lion
         ),
 
         MODEL_TENSOR.ATTN_K_NORM: (
             "language_model.encoder.layers.{bid}.self_attention.k_layernorm",
             "model.layers.{bid}.self_attn.k_layernorm",                       # persimmon
-            "transformer.blocks.{bid}.attn.k_ln",
+            "transformer.blocks.{bid}.attn.k_ln",                             # sea-lion
         ),
 
         MODEL_TENSOR.ROPE_FREQS: (
diff --git a/llama.cpp b/llama.cpp
index cc8b2ac40..d24c7aa37 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -4746,7 +4746,7 @@ static bool llm_load_tensors(
             case LLM_ARCH_MPT:
                 {
                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
-                    model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD,   "weight"),   {n_embd, hparams.n_ctx_train});
+                    model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD,   "weight"),   {n_embd, hparams.n_ctx_train}, false);
 
                     // output
                     {
@@ -4785,11 +4785,11 @@ static bool llm_load_tensors(
                         layer.ffn_up     = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
                         layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP,   "bias", i),   {n_ff}, false);
 
-                        layer.attn_q_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd});
-                        layer.attn_q_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "bias",   i), {n_embd});
+                        layer.attn_q_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd}, false);
+                        layer.attn_q_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "bias",   i), {n_embd}, false);
 
-                        layer.attn_k_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd});
-                        layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias",   i), {n_embd});                        
+                        layer.attn_k_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd}, false);
+                        layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias",   i), {n_embd}, false);                        
 
                         // AWQ ScaleActivation layer
                         layer.ffn_act = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, false);