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 : add support for larger Granite Code Models (20B, 34B) (#7324)

Browse Source 
Tie the weights for ARCH_STARCODER to support the larger Granite code models.
Partially addresses ggerganov/issues/7116

There still remains to be a few things to fix.
Currently requires `--override-kv tokenizer.ggml.add_bos_token=bool:false`
This commit is contained in:
Steffen Röcker
2024-05-18 10:04:55 +02:00
committed by GitHub
parent ca57e0f35e
commit 0f98acfac6
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
llama.cpp
View File

@@ -5188,7 +5188,14 @@ static bool llm_load_tensors(
{ {
model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 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_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}); model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false);
if (!model.output) {
// needs to be on GPU
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
ml.n_created--; // artificial tensor
ml.size_data += ggml_nbytes(model.output);
}
} }
for (int i = 0; i < n_layer; ++i) { for (int i = 0; i < n_layer; ++i) {