Skip to content

Append mult-eos,half-rope,bos to GLM4-0414 and Z #13021

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 23, 2025
Merged

Append mult-eos,half-rope,bos to GLM4-0414 and Z #13021

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a631456
append mult-eos,half-rope,bos to GLM4-0414
piDack Apr 19, 2025
4fdc52f
remove unset var
piDack Apr 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 16 additions & 1 deletion convert_hf_to_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4934,10 +4934,25 @@ class Glm4Model(Model):
model_arch = gguf.MODEL_ARCH.GLM4

def set_vocab(self):
self._set_vocab_gpt2()
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(self.dir_model, trust_remote_code=True)
special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=True)
tokens, toktypes, tokpre = self.get_vocab_base()
self.gguf_writer.add_tokenizer_model("gpt2")
self.gguf_writer.add_tokenizer_pre(tokpre)
self.gguf_writer.add_token_list(tokens)
self.gguf_writer.add_token_types(toktypes)
special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=True)
special_vocab._set_special_token("eos", tokenizer.get_added_vocab()["<|endoftext|>"])
special_vocab._set_special_token("eot", tokenizer.get_added_vocab()["<|user|>"])
special_vocab._set_special_token("unk", tokenizer.get_added_vocab()["<|endoftext|>"])
special_vocab._set_special_token("bos", tokenizer.get_added_vocab()["[gMASK]"])
special_vocab.add_to_gguf(self.gguf_writer)

def set_gguf_parameters(self):
super().set_gguf_parameters()
rope_dim = self.hparams["head_dim"]
self.gguf_writer.add_rope_dimension_count(int(rope_dim * self.hparams.get("partial_rotary_factor", 0.5)))
if self.hparams.get("rope_scaling") is not None and "factor" in self.hparams["rope_scaling"]:
if self.hparams["rope_scaling"].get("type") == "yarn":
self.gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.YARN)
Expand Down