46 lines
1.1 KiB
JSON
46 lines
1.1 KiB
JSON
{
|
|
"alpha_pattern": {},
|
|
"auto_mapping": {
|
|
"base_model_class": "Qwen3ForCausalLM",
|
|
"parent_library": "transformers.models.qwen3.modeling_qwen3",
|
|
"unsloth_fixed": true
|
|
},
|
|
"base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
|
|
"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": 16,
|
|
"lora_bias": false,
|
|
"lora_dropout": 0.0,
|
|
"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": [
|
|
"up_proj",
|
|
"o_proj",
|
|
"k_proj",
|
|
"gate_proj",
|
|
"q_proj",
|
|
"down_proj",
|
|
"v_proj"
|
|
],
|
|
"target_parameters": null,
|
|
"task_type": "CAUSAL_LM",
|
|
"trainable_token_indices": null,
|
|
"use_dora": false,
|
|
"use_qalora": false,
|
|
"use_rslora": true
|
|
} |