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

Assume tied weights if lm_head/output weights is missing.

Browse source 
This is to support model configurations with "tie_word_embeddings" set to true.
This commit is contained in:
Don Mahurin 2024-03-01 11:49:53 -08:00
parent c29af7e225
commit b59615fa42
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

@ -3855,7 +3855,13 @@ static bool llm_load_tensors(
{ {
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){ if (model.arch != LLM_ARCH_MINICPM){
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);
}
} }
} }