From b22ed8bc669fff293dfe8cc95209f46adacb862c Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Mon, 27 Jan 2025 17:47:24 +0200 Subject: [PATCH] Be able to load Deepseek-v2-Lite --- src/llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama.cpp b/src/llama.cpp index a7f46fed..b6a4a06d 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -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);