diff options
| author | slaren <slarengh@gmail.com> | 2024-05-22 16:10:46 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-22 16:10:46 +0200 |
| commit | b18532a4efeca8796fea8e36195c81cbfd596a4a (patch) | |
| tree | cc9966ee05ad20c4f554a430e2f4b03c40d75b8b /examples/llama-bench | |
| parent | fcda1128bc5f8eb7e1811708fe9d9867b9aec815 (diff) | |
phi3 : duplicate rope factors in each layer (#7447)
* phi3 : duplicate rope factors in each layer
phi3 : set phi-3 model type as 14B
model loader : simplify the process for duplicating model tensors
llama-bench : remove default pg test
* replace bool parameters in llama_model_loader with named flags
Diffstat (limited to 'examples/llama-bench')
| -rw-r--r-- | examples/llama-bench/llama-bench.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp index 8b965e19..6bb1f70c 100644 --- a/examples/llama-bench/llama-bench.cpp +++ b/examples/llama-bench/llama-bench.cpp @@ -195,7 +195,7 @@ static const cmd_params cmd_params_defaults = { /* model */ {"models/7B/ggml-model-q4_0.gguf"}, /* n_prompt */ {512}, /* n_gen */ {128}, - /* n_pg */ {{512, 128}}, + /* n_pg */ {}, /* n_batch */ {2048}, /* n_ubatch */ {512}, /* type_k */ {GGML_TYPE_F16}, |