Skip to content

Commit

Permalink
Merge branch 'ggerganov:master' into master
Browse files Browse the repository at this point in the history
  • Loading branch information
sealad886 authored May 3, 2024
2 parents 0d1a016 + 60325fa commit 1b73d22
Show file tree
Hide file tree
Showing 2 changed files with 2 additions and 2 deletions.
2 changes: 1 addition & 1 deletion convert-hf-to-gguf.py
Original file line number Diff line number Diff line change
Expand Up @@ -1433,7 +1433,7 @@ def write_tensors(self):
experts = dict()
for name, data_torch in self.get_tensors():
# we don't need these
if name.endswith((".attention.masked_bias", ".attention.bias", ".attention.rotary_emb.inv_freq")):
if name.endswith((".attention.masked_bias", ".attention.bias", ".rotary_emb.inv_freq")):
continue

old_dtype = data_torch.dtype
Expand Down
2 changes: 1 addition & 1 deletion llama.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -2359,7 +2359,7 @@ static bool llama_kv_cache_init(
cache.recurrent = model.arch == LLM_ARCH_MAMBA;
cache.v_trans = !cparams.flash_attn;

// TODO: support mixed reccurent Transformer architectues
// TODO: support mixed recurrent Transformer architectures
// NOTE: (!a || b) is a logical implication (a -> b)
GGML_ASSERT(!cache.recurrent || n_embd_k_gqa == hparams.n_embd_k_s());
GGML_ASSERT(!cache.recurrent || n_embd_v_gqa == hparams.n_embd_v_s());
Expand Down

0 comments on commit 1b73d22

Please sign in to comment.