CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix falcon arch for tied output embeddings (#4978)

Browse Source 
* falcon arch fix for tied output embeddings

* Update llama.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update llama.cpp

* Update llama.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update llama.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
John
2024-01-18 23:12:15 +01:00
committed by GitHub
parent 9b6ea4263a
commit 57e2a7a52a
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
llama.cpp
View File

@@ -3438,7 +3438,12 @@ static bool llm_load_tensors(
{
model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd});
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab});
if (gguf_find_tensor(ml.ctx_gguf, tn(LLM_TENSOR_OUTPUT, "weight").c_str()) >= 0) {
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab});
} else {
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU
ml.n_created--; // artificial tensor
}
}
for (int i = 0; i < n_layer; ++i) {