CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-05 09:36:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

small fix ffn_norm

Browse Source
This commit is contained in:
ibrahimkhadraoui
2025-07-04 15:37:40 +04:00
parent d22b4ea425
commit 15138df48f
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/gguf/tensor_mapping.py
View File

@@ -286,7 +286,7 @@ class TensorNameMap:
# Post feed-forward norm
MODEL_TENSOR.FFN_PRE_NORM: (
"model.layers.{bid}.pre_feedforward_layernorm", # gemma2
"model.layers.{bid}.pre_ff_layernorm.weight",
"model.layers.{bid}.pre_ff_layernorm.weight",
),
# Post feed-forward norm

2
src/llama-arch.cpp
View File

@@ -1068,7 +1068,7 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{ LLM_TENSOR_SSM_D, "blk.%d.ssm_d" },
{ LLM_TENSOR_SSM_NORM, "blk.%d.ssm_norm" },
{ LLM_TENSOR_SSM_OUT, "blk.%d.ssm_out" },
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
{ LLM_TENSOR_FFN_GATE, "blk.%d.ffn_gate" },
{ LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },

2
src/llama-model.cpp
View File

@@ -4595,7 +4595,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
// feed forward (w/ optional biases)
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_PRE_NORM, i), {hidden_size}, 0);
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.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);