mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

models : fix LFM2 tensors (#17548)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-11-27 16:04:29 +02:00
committed by GitHub
parent 909072abcf
commit 6783b11fb0
3 changed files with 12 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+4 -3
View File
@@ -6133,9 +6133,10 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
case LLM_ARCH_LFM2:
case LLM_ARCH_LFM2MOE:
{
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
tok_norm = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 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);
if (output == NULL) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);