root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

llama : fix t5 uses of n_head and n_ff

Browse Source
This commit is contained in:
Francis Couture-Harpin 2024-07-04 11:52:48 -04:00
parent c6ac198424
commit 18e92879d5
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/llama.cpp
View File

@ -5139,13 +5139,13 @@ static void llm_load_hparams(
case 6: model.type = e_model::MODEL_60M; break; // t5-small
case 8: model.type = e_model::MODEL_80M; break; // flan-t5-small
case 12:
switch (hparams.n_ff) {
switch (hparams.n_ff()) {
case 3072: model.type = e_model::MODEL_220M; break; // t5-base
case 2048: model.type = e_model::MODEL_250M; break; // flan-t5-base
default: model.type = e_model::MODEL_UNKNOWN;
} break;
case 24:
switch (hparams.n_ff) {
switch (hparams.n_ff()) {
case 4096: model.type = e_model::MODEL_770M; break; // t5-large
case 2816: model.type = e_model::MODEL_780M; break; // flan-t5-large
case 16384: model.type = e_model::MODEL_3B; break; // t5-3b
@ -7329,7 +7329,7 @@ static bool llm_load_tensors(
auto & layer = model.layers[i];
layer.attn_norm_enc = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ENC_ATTN_NORM, "weight", i), {n_embd});
layer.attn_rel_b_enc = ml.create_tensor(ctx_input, tn(LLM_TENSOR_ENC_ATTN_REL_B, "weight", i), {hparams.n_head, hparams.n_rel_attn_bkts}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.attn_rel_b_enc = ml.create_tensor(ctx_input, tn(LLM_TENSOR_ENC_ATTN_REL_B, "weight", i), {hparams.n_head(), hparams.n_rel_attn_bkts}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.wq_enc = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ENC_ATTN_Q, "weight", i), {n_embd, n_embd_k_gqa});
layer.wk_enc = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ENC_ATTN_K, "weight", i), {n_embd, n_embd_k_gqa});
@ -7342,7 +7342,7 @@ static bool llm_load_tensors(
layer.ffn_up_enc = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ENC_FFN_UP, "weight", i), {n_embd, n_ff});
layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_DEC_ATTN_NORM, "weight", i), {n_embd});
layer.attn_rel_b = ml.create_tensor(ctx_input, tn(LLM_TENSOR_DEC_ATTN_REL_B, "weight", i), {hparams.n_head, hparams.n_rel_attn_bkts}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.attn_rel_b = ml.create_tensor(ctx_input, tn(LLM_TENSOR_DEC_ATTN_REL_B, "weight", i), {hparams.n_head(), hparams.n_rel_attn_bkts}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_DEC_ATTN_Q, "weight", i), {n_embd, n_embd_k_gqa});
layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_DEC_ATTN_K, "weight", i), {n_embd, n_embd_k_gqa});
@ -7351,7 +7351,7 @@ static bool llm_load_tensors(
layer.attn_norm_cross = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_DEC_CROSS_ATTN_NORM, "weight", i), {n_embd});
// this tensor seems to be unused in HF transformers implementation
layer.attn_rel_b_cross = ml.create_tensor(ctx_input, tn(LLM_TENSOR_DEC_CROSS_ATTN_REL_B, "weight", i), {hparams.n_head, hparams.n_rel_attn_bkts}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.attn_rel_b_cross = ml.create_tensor(ctx_input, tn(LLM_TENSOR_DEC_CROSS_ATTN_REL_B, "weight", i), {hparams.n_head(), hparams.n_rel_attn_bkts}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.wq_cross = ml.create_tensor(ctx_split, tn(LLM_TENSOR_DEC_CROSS_ATTN_Q, "weight", i), {n_embd, n_embd_k_gqa});
layer.wk_cross = ml.create_tensor(ctx_split, tn(LLM_TENSOR_DEC_CROSS_ATTN_K, "weight", i), {n_embd, n_embd_k_gqa});