qwen35: use post-norm hidden state for MTP (#24025)
* qwen35: use post-norm hidden state for MTP * rename pre_norm to nextn * fix step35
This commit is contained in:
+2
-2
@@ -29,8 +29,8 @@ struct llama_cparams {
|
||||
float yarn_beta_slow;
|
||||
|
||||
bool embeddings;
|
||||
bool embeddings_pre_norm; // also extract the hidden state before the final output norm
|
||||
bool embeddings_pre_norm_masked; // extract for only rows where batch.logits != 0
|
||||
bool embeddings_nextn; // also extract the hidden state before the final output norm
|
||||
bool embeddings_nextn_masked; // extract for only rows where batch.logits != 0
|
||||
bool causal_attn;
|
||||
bool offload_kqv;
|
||||
bool flash_attn;
|
||||
|
||||
Reference in New Issue
Block a user