bridge.models.minicpmo.minicpmo_bridge#
MiniCPM-o 4.5 registration using Qwen3’s existing conversion rules.
Module Contents#
Classes#
Convert the understanding stage while preserving MiniCPM-o identity. |
API#
- class bridge.models.minicpmo.minicpmo_bridge.MiniCPMOBridge#
Bases:
megatron.bridge.models.qwen.qwen3_bridge.Qwen3BridgeConvert the understanding stage while preserving MiniCPM-o identity.
The language weights are Qwen3 weights under
llm. Perception weights are replicated and retain their Hugging Face names underperception. TTS is deliberately excluded from this understanding-stage model.- MODEL_CONFIG_CLASS#
None
- USE_MODEL_CONFIG_FOR_CONVERSION#
True
- HF_EXPORT_IGNORED_SOURCE_PREFIXES#
(‘tts.’,)
- ADDITIONAL_FILE_PATTERNS#
[‘tokenizer*.json’, ‘special_tokens_map.json’, ‘chat_template.jinja’, ‘preprocessor_config.json’, ‘p…
- postprocess_hf_export_artifacts(path: pathlib.Path) None#
Keep component metadata compatible with the native processor loader.
The native processor receives its components as positional arguments. Newer Transformers also serializes them inside processor_config.json, which supplies the same arguments twice when loaded by native HF 4.51. Component settings remain in the preserved source artifact files.
- hf_config_to_model_config_kwargs(
- hf_config: transformers.PretrainedConfig,
Use Qwen3 language conversion and retain the perception configuration.
- classmethod megatron_to_hf_config(
- provider: megatron.bridge.models.minicpmo.minicpmo_config.MiniCPMOModelConfig,
Preserve perception configuration when exporting understanding weights.
- mapping_registry() megatron.bridge.models.conversion.mapping_registry.MegatronMappingRegistry#
Namespace Qwen3 mappings and add replicated perception parameters.