| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": { | |
| "base_model_class": "LLaDA2MoeModelLM", | |
| "parent_library": "dllm.pipelines.llada21.models.modeling_llada2_moe" | |
| }, | |
| "base_model_name_or_path": "ML-GSAI/LLaDA2.1-mini", | |
| "bias": "none", | |
| "corda_config": null, | |
| "eva_config": null, | |
| "exclude_modules": null, | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 64, | |
| "lora_bias": false, | |
| "lora_dropout": 0.05, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "qalora_group_size": 16, | |
| "r": 32, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "dense", | |
| "up_proj", | |
| "down_proj", | |
| "gate_proj", | |
| "query_key_value" | |
| ], | |
| "target_parameters": null, | |
| "task_type": null, | |
| "trainable_token_indices": null, | |
| "use_dora": false, | |
| "use_qalora": false, | |
| "use_rslora": false | |
| } |