CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : remove unnecessary chat template patching (#17289)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-11-15 20:58:59 +01:00
committed by GitHub
parent 24dc769f1b
commit 662192e1dc
1 changed files with 0 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
convert_hf_to_gguf.py
View File

@@ -7840,12 +7840,6 @@ class Glm4MoeModel(TextModel):
special_vocab._set_special_token("unk", tokenizer.get_added_vocab()["<|endoftext|>"]) # 151329
special_vocab._set_special_token("eom", tokenizer.get_added_vocab()["<|observation|>"]) # 151338
# Patch broken chat template
if isinstance(special_vocab.chat_template, str) and "visible_text(m.content).endswith" in special_vocab.chat_template:
special_vocab.chat_template = special_vocab.chat_template.replace(
"""{{ visible_text(m.content) }}\n{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}""",
"""{% set content = visible_text(m.content) %}{{ content }}\n{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not content.endswith("/nothink")) else '' -}}""")
special_vocab.add_to_gguf(self.gguf_writer)
def set_gguf_parameters(self):
@@ -9395,16 +9389,6 @@ class HunYuanModel(TextModel):
class SmolLM3Model(LlamaModel):
model_arch = gguf.MODEL_ARCH.SMOLLM3
def set_vocab(self):
super().set_vocab()
# remove unsupported array slicing in chat template
# ref: https://huggingface.co/ggml-org/SmolLM3-3B-GGUF/discussions/1
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(self.dir_model)
if tokenizer.chat_template is not None:
chat_template = tokenizer.chat_template.replace("[:]", "")
self.gguf_writer.add_chat_template(chat_template)
@ModelBase.register("GptOssForCausalLM")
class GptOssModel(TextModel):