ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 23:24:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Be able to load Deepseek-v2-Lite

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-01-27 17:47:24 +02:00
parent 2d34c55b6f
commit b22ed8bc66
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@@ -7650,7 +7650,7 @@ static bool llm_load_tensors(
layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff});
} else {
layer.ffn_gate_inp = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert});
layer.ffn_exp_probs_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert} );
layer.ffn_exp_probs_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, 1);
GGML_ASSERT(n_expert > 0);
GGML_ASSERT(n_expert_used > 0);