diff options
author | Stephan Walter <stephan@walter.name> | 2023-03-28 15:56:03 +0000 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-03-28 18:56:03 +0300 |
commit | c1f885067c61191a07a1aedf684168dda62f3f71 (patch) | |
tree | 2bcb3f068942e2f16a92d70fec4bd623ac17ce28 /llama.h | |
parent | e0670260fb50a882b37074112b1881fb0820cf77 (diff) |
ggml : introduce structs for the q4 data blocks (#356)
* Introduce structs for the q4 data blocks
* ggml : rename quant struct variables + fix ARM_NEON
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'llama.h')
-rw-r--r-- | llama.h | 3 |
1 files changed, 1 insertions, 2 deletions
@@ -81,8 +81,7 @@ extern "C" { LLAMA_API int llama_model_quantize( const char * fname_inp, const char * fname_out, - int itype, - int qk); + int itype); // Run the llama inference to obtain the logits and probabilities for the next token. // tokens + n_tokens is the provided batch of new tokens to process |