tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : Append mult-eos,half-rope,bos to GLM4-0414 and Z (#13021)

Browse Source 
* append mult-eos,half-rope,bos to GLM4-0414

* remove unset var
This commit is contained in:
piDack
2025-04-23 22:59:14 +08:00
committed by GitHub
parent 2cca6c01e4
commit eb1776b15a
1 changed files with 16 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
convert_hf_to_gguf.py
View File

@ -5079,10 +5079,25 @@ class Glm4Model(TextModel):
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)