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

Qwen2: assume tied weights if lm_head/output weights is missing

Browse source
This commit is contained in:
Ren Xuancheng 2024-04-18 17:52:43 +08:00 • committed by GitHub
parent 3b8f1ec4b1
commit c7ab76eacc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 7 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama.cpp
View file

@ -5184,7 +5184,13 @@ static bool llm_load_tensors(
// output
{
model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {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_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) {