Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <[email protected]>

Author: younesbelkada

src/llama-model.cpp

@@ -4550,17 +4550,17 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                         /*SSM LAYERS*/
                         // ssm in
                         layer.ssm_in = create_tensor(tn(LLM_TENSOR_SSM_IN, "weight", i), {hidden_size, ssm_projection_size}, 0);
-                        layer.ssm_in_b = create_tensor(tn(LLM_TENSOR_SSM_IN, "bias", i), {n_embd, ssm_projection_size}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                        layer.ssm_in_b = create_tensor(tn(LLM_TENSOR_SSM_IN, "bias", i), {n_embd, ssm_projection_size}, TENSOR_NOT_REQUIRED);
                         // ssm 1d conv
                         layer.ssm_conv1d = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {ssm_conv_kernel_size, ssm_conv_dim}, 0);
-                        layer.ssm_conv1d_b = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {ssm_conv_dim}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                        layer.ssm_conv1d_b = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {ssm_conv_dim}, TENSOR_NOT_REQUIRED);
                         // ssm_dt
                         layer.ssm_dt_b = create_tensor(tn(LLM_TENSOR_SSM_DT, "bias", i), {ssm_num_heads}, 0);
                         // no "weight" suffix for these
                         layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A, i), {1, ssm_num_heads}, 0);
                         layer.ssm_d = create_tensor(tn(LLM_TENSOR_SSM_D, i), {1, ssm_num_heads}, 0);
                         // ssm_norm
-                        layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", i), {ssm_intermediate_size / ssm_n_groups, ssm_n_groups}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                        layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", i), {ssm_intermediate_size / ssm_n_groups, ssm_n_groups}, TENSOR_NOT_REQUIRED);
                         // out_proj
                         layer.ssm_out = create_tensor(tn(LLM_TENSOR_SSM_OUT, "weight", i), {ssm_intermediate_size, hidden_size}, 0);
 
@@ -4570,23 +4570,23 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                         layer.wk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "weight", i), {hidden_size, attn_num_key_value_head * n_embd_head_k}, 0);
                         layer.wv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "weight", i), {hidden_size, attn_num_key_value_head * n_embd_head_v}, 0);
                         layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * attn_num_attention_head, hidden_size}, 0);
-                        layer.bq = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "bias", i), {hidden_size},         llama_model_loader::TENSOR_NOT_REQUIRED);
-                        layer.bk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "bias", i), {attn_num_key_value_head * n_embd_head_k}, llama_model_loader::TENSOR_NOT_REQUIRED);
-                        layer.bv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "bias", i), {attn_num_key_value_head * n_embd_head_v}, llama_model_loader::TENSOR_NOT_REQUIRED);
-                        layer.bo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {hidden_size},         llama_model_loader::TENSOR_NOT_REQUIRED);
+                        layer.bq = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "bias", i), {hidden_size}, TENSOR_NOT_REQUIRED);
+                        layer.bk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "bias", i), {attn_num_key_value_head * n_embd_head_k}, TENSOR_NOT_REQUIRED);
+                        layer.bv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "bias", i), {attn_num_key_value_head * n_embd_head_v}, TENSOR_NOT_REQUIRED);
+                        layer.bo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {hidden_size}, TENSOR_NOT_REQUIRED);
                         layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {hidden_size}, 0);
 
 
                         // feed forward (w/ optional biases)
                         layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, i), {hidden_size}, 0);
-                        layer.rope_freqs = create_tensor(tn(LLM_TENSOR_ROPE_FREQS, "weight", i), {n_rot/2}, llama_model_loader::TENSOR_NOT_REQUIRED | (i != 0 ? llama_model_loader::TENSOR_DUPLICATED : 0));
+                        layer.rope_freqs = create_tensor(tn(LLM_TENSOR_ROPE_FREQS, "weight", i), {n_rot/2}, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 0));
                         layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {hidden_size,   ffn_intermediate_size}, 0);
                         layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  ffn_intermediate_size, hidden_size}, 0);
                         layer.ffn_up   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), {hidden_size,   ffn_intermediate_size}, 0);
 
-                        layer.ffn_gate_b = create_tensor(tn(LLM_TENSOR_FFN_GATE, "bias", i), {ffn_intermediate_size}, llama_model_loader::TENSOR_NOT_REQUIRED);
-                        layer.ffn_down_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "bias", i), {hidden_size}, llama_model_loader::TENSOR_NOT_REQUIRED);
-                        layer.ffn_up_b   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "bias", i), {ffn_intermediate_size}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                        layer.ffn_gate_b = create_tensor(tn(LLM_TENSOR_FFN_GATE, "bias", i), {ffn_intermediate_size}, TENSOR_NOT_REQUIRED);
+                        layer.ffn_down_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "bias", i), {hidden_size}, TENSOR_NOT_REQUIRED);
+                        layer.ffn_up_b   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "bias", i), {ffn_intermediate_size}, TENSOR_NOT_REQUIRED);
                     }
                 } break;
             case LLM_ARCH_HUNYUAN_MOE: