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

llama: dbrx: fix ggml context of the attention outputs weight

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-04-09 00:58:50 +02:00
parent 55943a281f
commit c7b9a2e85e
1 changed files with 1 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama.cpp
View file

@ -4690,7 +4690,7 @@ static bool llm_load_tensors(
layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa});
layer.wo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
layer.attn_out_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd});
@ -4698,7 +4698,6 @@ static bool llm_load_tensors(
layer.ffn_gate_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE_EXPS,"weight", i), {n_embd, n_ff, n_expert});
layer.ffn_down_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN_EXPS,"weight", i), {n_ff, n_embd, n_expert});
layer.ffn_up_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), {n_embd, n_ff, n_expert});
}
} break;
case LLM_ARCH_BAICHUAN: