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

gguf : quantization is working

Browse Source
This commit is contained in:
M. Yusuf Sarıgöz
2023-08-12 16:39:05 +03:00
parent 1fc3d30b71
commit 202eab04d3
3 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
gguf-llama.cpp
View File

@@ -752,7 +752,6 @@ struct gguf_file_saver {
file.seek(info_offset, SEEK_SET);
GGML_ASSERT(info_offset == file.tell());
total_written += file.write_str(tensor.name);
printf("total_written = %zu, name = %s\n", total_written, tensor.name.c_str());
int32_t n_dims = tensor.ne.size();
total_written += file.write_i32(n_dims);
@@ -765,8 +764,7 @@ printf("total_written = %zu, name = %s\n", total_written, tensor.name.c_str());
info_offset += total_written;
file.seek(0, SEEK_END);
printf("total_written = %zu\n", total_written);
return total_written;
}
@@ -936,8 +934,7 @@ struct llama_model_loader {
} else {
gguf_file & file = file_loader->file;
file.seek(lt.file_off, SEEK_SET);
// TODO
//file.read_raw(lt.data, lt.size);
file.read_raw(lt.data, lt.size);
}
if (0) {