ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

clip : fix confused naming ffn_up and ffn_down (#13290)

Browse source 
* clip :  fix confused naming ffn_up and ffn_down

* rm ffn_i/o/g naming

* rename n_embd, n_ff

* small fix

* no check n_ff
This commit is contained in:
Xuan-Son Nguyen 2025-05-05 12:54:44 +02:00 • committed by GitHub
parent ae803bfc3d
commit 5215b91e93
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 86 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

6
convert_hf_to_gguf.py
View file

@ -1778,6 +1778,12 @@ class LlamaModel(TextModel):
model_arch = gguf.MODEL_ARCH.LLAMA
undo_permute = True
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# fix for SmolVLM2, missing `num_attention_heads` in config.json
if self.hf_arch == "VLlama3ForCausalLM":
self.hparams["num_attention_heads"] = self.hparams.get("num_attention_heads", 32)
def set_vocab(self):
try:
self._set_vocab_sentencepiece()