CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : support output bias for qwen2 (#14711)

Browse Source 
Co-authored-by: qwaqrm <qwaqrm@126.com>
This commit is contained in:
tempstudio
2025-07-16 10:02:06 -05:00
committed by GitHub
parent 225e7a1438
commit b0f0ecc3dc
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llama-model.cpp
View File

@@ -2692,6 +2692,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
// output // output
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0); output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED); output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
output_b = create_tensor(tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}, TENSOR_NOT_REQUIRED);
// if output is NULL, init from the input tok embed // if output is NULL, init from the input tok embed
if (output == NULL) { if (output == NULL) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
@@ -7765,6 +7766,10 @@ struct llm_build_qwen2 : public llm_graph_context {
// lm_head // lm_head
cur = build_lora_mm(model.output, cur); cur = build_lora_mm(model.output, cur);
if (model.output_b != nullptr) {
cur = ggml_add(ctx0, cur, model.output_b);
}
cb(cur, "result_output", -1); cb(cur, "result_output", -1);
res->t_logits = cur; res->t_logits = cur;