llama : fix typo in llama_tensor_get_type comment [no ci] (#8937)
This commit is contained in:
parent
daef3ab233
commit
6f6496bb09
1 changed files with 1 additions and 1 deletions
|
@ -15304,7 +15304,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
|
|||
const int n_expert = std::max(1, (int)qs.model.hparams.n_expert);
|
||||
auto layer_info = [n_expert] (int i_layer, int n_layer, const char * name) {
|
||||
if (n_expert > 1) {
|
||||
// Believe it or not, "experts" in the FFN of Mixtral-8x7B are not consecutive, but iccasionally randomly
|
||||
// Believe it or not, "experts" in the FFN of Mixtral-8x7B are not consecutive, but occasionally randomly
|
||||
// sprinkled in the model. Hence, simply dividing i_ffn_down by n_expert does not work
|
||||
// for getting the current layer as I initially thought, and we need to resort to parsing the
|
||||
// tensor name.
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue