tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-15 15:17:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : fix smollm3 jinja template (#14586)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2025-07-09 08:26:13 +02:00
committed by GitHub
parent 6efcd65945
commit 20b7bf8a32
1 changed files with 10 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
convert_hf_to_gguf.py
View File

@ -6692,6 +6692,16 @@ class HunYuanMoEModel(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)
###### CONVERSION LOGIC ######