vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

typo correction (#8891)

Browse source
This commit is contained in:
Nexes the Old 2024-08-07 01:41:54 +02:00 • committed by GitHub
parent 1e6f6554aa
commit 31958546c3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
include/llama.h
View file

@ -345,7 +345,7 @@ extern "C" {
int32_t nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency() int32_t nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
enum llama_ftype ftype; // quantize to this llama_ftype enum llama_ftype ftype; // quantize to this llama_ftype
enum ggml_type output_tensor_type; // output tensor type enum ggml_type output_tensor_type; // output tensor type
enum ggml_type token_embedding_type; // itoken embeddings tensor type enum ggml_type token_embedding_type; // token embeddings tensor type
bool allow_requantize; // allow quantizing non-f32/f16 tensors bool allow_requantize; // allow quantizing non-f32/f16 tensors
bool quantize_output_tensor; // quantize output.weight bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored