ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Keep standalone chat templates in the scoped video download

Browse source 
tokenizer/chat_template.jinja ships as its own file in the LTX-2 and
HunyuanVideo-1.5 repos and apply_chat_template reads it at generation
time, so a scoped snapshot without it loads fine and then crashes the
first generation.
This commit is contained in:
Daniel Han 2026-07-05 05:32:24 +00:00
commit 14f4e7ef7c
2 changed files with 10 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
studio/backend/core/inference/video.py
View file

@ -406,7 +406,11 @@ class VideoBackend:
files: list[tuple[str, int]] = []
for sibling in info.siblings or []:
name, size = sibling.rfilename, sibling.size or 0
if not name.endswith((".safetensors", ".json", ".model", ".txt")):
# .jinja: tokenizer/chat_template.jinja ships as a standalone file in the
# LTX-2 and HunyuanVideo-1.5 repos (not embedded in tokenizer_config.json)
# and apply_chat_template needs it at generation time, so a snapshot
# without it loads fine and then crashes the first generation.
if not name.endswith((".safetensors", ".json", ".model", ".txt", ".jinja")):
continue
if "/" not in name and name.endswith(".safetensors"):
continue

6
studio/backend/tests/test_video_backend.py
View file

@ -459,6 +459,7 @@ _LTX2_SIBLINGS = [
_sibling("text_encoder/diffusion_pytorch_model-00002-of-00002.safetensors", 25),
_sibling("vae/diffusion_pytorch_model.safetensors", 3),
_sibling("tokenizer/tokenizer.model", 1),
_sibling("tokenizer/chat_template.jinja", 1),
_sibling("assets/example.mp4", 500),
]
@ -473,7 +474,10 @@ def test_base_download_files_scopes_pipeline_pull():
assert "assets/example.mp4" not in files
assert files["text_encoder/model-00001-of-00002.safetensors"] == 25
assert files["transformer/diffusion_pytorch_model-00001-of-00002.safetensors"] == 20
assert sum(files.values()) == 10 + 1 + 20 + 18 + 25 + 25 + 3 + 1
# The standalone chat template must survive the whitelist: apply_chat_template
# reads it at generation time and it is not embedded in tokenizer_config.json.
assert "tokenizer/chat_template.jinja" in files
assert sum(files.values()) == 10 + 1 + 20 + 18 + 25 + 25 + 3 + 1 + 1
def test_base_download_files_gguf_drops_transformer():