diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2024-01-12 13:01:56 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-12 13:01:56 +0200 |
| commit | f445c0e68cf8e1faca0b2aa8dfb9d48231cec301 (patch) | |
| tree | a230e263424ba71153764e21fef7b92f46bd9fd9 /common/common.cpp | |
| parent | 326b418b59b6d48d854c4461a2303e8ac0a311e6 (diff) | |
llama : fix llm_build_k_shift to use correct n_rot (#4889)
* llama : fix llm_build_k_shift to use correct n_rot
ggml-ci
* llama : always use hparams.n_rot for ggml_rope_custom
ggml-ci
* convert : fix persimmon conversion to write correct n_rot
Diffstat (limited to 'common/common.cpp')
| -rw-r--r-- | common/common.cpp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/common/common.cpp b/common/common.cpp index b2cb0e25..3aefed01 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1055,6 +1055,9 @@ struct llama_model_params llama_model_params_from_gpt_params(const gpt_params & } static ggml_type kv_cache_type_from_str(const std::string & s) { + if (s == "f32") { + return GGML_TYPE_F32; + } if (s == "f16") { return GGML_TYPE_F16; } |