root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-28 12:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Update llama.cpp

Browse Source
This commit is contained in:
Sourab Mangrulkar 2024-03-01 12:35:18 +05:30
parent 10aa6e927e
commit 5c06625f58
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llama.cpp
View File

@ -4529,7 +4529,14 @@ static bool llm_load_tensors(
{
model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd});
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab});
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_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
ml.n_created--; // artificial tensor
}
}
for (int i = 0; i < n_layer; ++i) {
@ -4560,7 +4567,7 @@ static bool llm_load_tensors(
// optional bias tensors
layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, false);
layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP , "bias", i), { n_embd}, false);
layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP , "bias", i), { n_ff}, false);
}
} break;
default: