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

modified the general name of glm model

Browse source
This commit is contained in:
toyer 2024-07-01 03:31:50 +00:00
parent 5e9dba664a
commit 865dd03f43
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert-hf-to-gguf.py
View file

@ -3104,7 +3104,7 @@ class ChatGLMModel(Model):
special_vocab.add_to_gguf(self.gguf_writer) special_vocab.add_to_gguf(self.gguf_writer)
def set_gguf_parameters(self): def set_gguf_parameters(self):
self.gguf_writer.add_name(self.dir_model.name) self.gguf_writer.add_name(self.hparams.get("_name_or_path").split("/")[1]) # THUDM/glm4-9b-chat or THUDM/chatglm3-6b
n_embed = self.hparams.get("hidden_size", self.hparams.get("n_embed")) n_embed = self.hparams.get("hidden_size", self.hparams.get("n_embed"))
n_head = self.hparams.get("n_head", self.hparams.get("num_attention_heads")) n_head = self.hparams.get("n_head", self.hparams.get("num_attention_heads"))
n_head_kv = self.hparams.get("multi_query_group_num", n_head) n_head_kv = self.hparams.get("multi_query_group_num", n_head)