Merge 228d573424 into ec2b787ebe
This commit is contained in:
commit
20f8672596
|
|
@ -1271,7 +1271,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
|
|||
llama_model_quantize_params llama_model_quantize_default_params() {
|
||||
llama_model_quantize_params result = {
|
||||
/*.nthread =*/ 0,
|
||||
/*.ftype =*/ LLAMA_FTYPE_MOSTLY_Q5_1,
|
||||
/*.ftype =*/ LLAMA_FTYPE_MOSTLY_Q8_0,
|
||||
/*.output_tensor_type =*/ GGML_TYPE_COUNT,
|
||||
/*.token_embedding_type =*/ GGML_TYPE_COUNT,
|
||||
/*.allow_requantize =*/ false,
|
||||
|
|
|
|||
Loading…
Reference in New Issue