model : fix DFlash output head sharing (#30111)
* llama : fix DFlash output head sharing Assisted-by: Codex * dflash : read tied output weights from GGUF metadata Assisted-by: Codex * llama : share tied word embedding metadata Assisted-by: Codex * llama : remove DFlash embedding head fallback Assisted-by: Codex
This commit is contained in:
1 parent
fc9ce6b9d5
commit
a11f57ba93
2 files changed
+2
-5
No files matched your search
@@ -167,9 +167,6 @@ void llama_model_dflash::load_arch_tensors(llama_model_loader &) {
|
||||
// optional: reduced-vocab drafts ship their own lm head, full-vocab drafts can share the target's via ctx_other
|
||||
// a draft with its own embeddings + head references no target tensors and can run on devices the target does not use (e.g. -devd with a tensor-split target)
|
||||
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), { n_embd, n_vocab_draft }, TENSOR_NOT_REQUIRED);
|
||||
if (output == nullptr && tok_embd != nullptr) {
|
||||
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab_draft }, TENSOR_DUPLICATED);
|
||||
}
|
||||
|
||||
if (hparams.dsv4_hc_mult > 0) {
|
||||
const int64_t q_lora_rank = hparams.n_lora_q;
|
||||
|
||||
Reference in new issue
Block a user