vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix

Browse source
This commit is contained in:
zhangkaihuo 2024-04-16 20:34:21 +08:00
parent 4da6e3e3e4
commit 1cd0a03720
1 changed files with 1 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama.cpp
View file

@ -4601,18 +4601,7 @@ static bool llm_load_tensors(
} }
// output // output
{
model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
if (model.arch != LLM_ARCH_MINICPM){
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false);
// if output is NULL, init from the input tok embed
if (model.output == NULL) {
model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
ml.n_created--; // artificial tensor
ml.size_data += ggml_nbytes(model.output);
}
}
}
for (int i = 0; i < n_layer; ++i) { for (int i = 0; i < n_layer; ++i) {
ggml_context * ctx_layer = ctx_for_layer(i); ggml_context * ctx_layer = ctx_for_layer(i);