Skip to content

convert : fix qwen omni conversion #13859

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.

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
May 28, 2025
Merged
Changes from all commits
Commits
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
18 changes: 9 additions & 9 deletions convert_hf_to_gguf.py
Original file line number Diff line number Diff line change
Expand Up @@ -423,19 +423,19 @@ def load_hparams(dir_model: Path):
try:
# for security reason, we don't allow loading remote code by default
# if a model need remote code, we will fallback to config.json
return AutoConfig.from_pretrained(dir_model, trust_remote_code=False).to_dict()
config = AutoConfig.from_pretrained(dir_model, trust_remote_code=False).to_dict()
except Exception as e:
logger.warning(f"Failed to load model config from {dir_model}: {e}")
logger.warning("Trying to load config.json instead")
with open(dir_model / "config.json", "r", encoding="utf-8") as f:
config = json.load(f)
if "llm_config" in config:
# rename for InternVL
config["text_config"] = config["llm_config"]
if "thinker_config" in config:
# rename for Qwen2.5-Omni
config["text_config"] = config["thinker_config"]["text_config"]
return config
if "llm_config" in config:
# rename for InternVL
config["text_config"] = config["llm_config"]
if "thinker_config" in config:
# rename for Qwen2.5-Omni
config["text_config"] = config["thinker_config"]["text_config"]
return config

@classmethod
def register(cls, *names: str) -> Callable[[AnyModel], AnyModel]:
Expand Down Expand Up @@ -1207,7 +1207,7 @@ def set_gguf_parameters(self):
self.gguf_writer.add_audio_block_count(self.find_aparam(self.n_block_keys))
self.gguf_writer.add_audio_head_count(self.find_aparam(["num_attention_heads"]))

else:
if not self.has_vision_encoder and not self.has_audio_encoder:
raise ValueError("MmprojModel must have either vision or audio encoder")

def write_vocab(self):
Expand Down