109 lines
2.7 KiB
JSON
109 lines
2.7 KiB
JSON
|
{
|
||
|
|
"alpha_pattern": {},
|
||
|
|
"auto_mapping": {
|
||
|
|
"base_model_class": "Qwen2ForCausalLM",
|
||
|
|
"parent_library": "transformers.models.qwen2.modeling_qwen2",
|
||
|
|
"unsloth_fixed": true
|
||
|
|
},
|
||
|
|
"base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct",
|
||
|
|
"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": 0.0,
|
||
|
|
"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": [
|
||
|
|
"layers.3.mlp.down_proj",
|
||
|
|
"layers.10.mlp.down_proj",
|
||
|
|
"layers.4.mlp.gate_proj",
|
||
|
|
"layers.9.mlp.down_proj",
|
||
|
|
"layers.5.k_proj",
|
||
|
|
"layers.9.k_proj",
|
||
|
|
"layers.2.mlp.down_proj",
|
||
|
|
"layers.7.mlp.up_proj",
|
||
|
|
"layers.10.k_proj",
|
||
|
|
"layers.9.mlp.gate_proj",
|
||
|
|
"layers.8.o_proj",
|
||
|
|
"layers.3.v_proj",
|
||
|
|
"layers.8.mlp.up_proj",
|
||
|
|
"layers.3.o_proj",
|
||
|
|
"layers.2.mlp.gate_proj",
|
||
|
|
"layers.8.q_proj",
|
||
|
|
"layers.8.v_proj",
|
||
|
|
"layers.6.mlp.gate_proj",
|
||
|
|
"layers.2.k_proj",
|
||
|
|
"layers.3.mlp.up_proj",
|
||
|
|
"layers.4.v_proj",
|
||
|
|
"layers.5.v_proj",
|
||
|
|
"layers.7.mlp.gate_proj",
|
||
|
|
"layers.3.q_proj",
|
||
|
|
"layers.7.q_proj",
|
||
|
|
"layers.8.mlp.gate_proj",
|
||
|
|
"layers.8.k_proj",
|
||
|
|
"layers.4.q_proj",
|
||
|
|
"layers.8.mlp.down_proj",
|
||
|
|
"layers.1.mlp.gate_proj",
|
||
|
|
"layers.2.mlp.up_proj",
|
||
|
|
"layers.3.k_proj",
|
||
|
|
"layers.2.v_proj",
|
||
|
|
"layers.1.mlp.down_proj",
|
||
|
|
"layers.10.v_proj",
|
||
|
|
"layers.2.q_proj",
|
||
|
|
"layers.9.o_proj",
|
||
|
|
"layers.4.mlp.up_proj",
|
||
|
|
"layers.6.v_proj",
|
||
|
|
"layers.7.v_proj",
|
||
|
|
"layers.5.q_proj",
|
||
|
|
"layers.1.k_proj",
|
||
|
|
"layers.1.v_proj",
|
||
|
|
"layers.4.k_proj",
|
||
|
|
"layers.6.q_proj",
|
||
|
|
"layers.6.k_proj",
|
||
|
|
"layers.7.mlp.down_proj",
|
||
|
|
"layers.4.mlp.down_proj",
|
||
|
|
"layers.10.mlp.gate_proj",
|
||
|
|
"layers.3.mlp.gate_proj",
|
||
|
|
"layers.9.q_proj",
|
||
|
|
"layers.10.q_proj",
|
||
|
|
"layers.1.o_proj",
|
||
|
|
"layers.1.mlp.up_proj",
|
||
|
|
"layers.5.mlp.up_proj",
|
||
|
|
"layers.7.o_proj",
|
||
|
|
"layers.9.mlp.up_proj",
|
||
|
|
"layers.10.mlp.up_proj",
|
||
|
|
"layers.6.o_proj",
|
||
|
|
"layers.10.o_proj",
|
||
|
|
"layers.2.o_proj",
|
||
|
|
"layers.5.mlp.down_proj",
|
||
|
|
"layers.6.mlp.down_proj",
|
||
|
|
"layers.5.o_proj",
|
||
|
|
"layers.6.mlp.up_proj",
|
||
|
|
"layers.9.v_proj",
|
||
|
|
"layers.4.o_proj",
|
||
|
|
"layers.1.q_proj",
|
||
|
|
"layers.7.k_proj",
|
||
|
|
"layers.5.mlp.gate_proj"
|
||
|
|
],
|
||
|
|
"target_parameters": null,
|
||
|
|
"task_type": "CAUSAL_LM",
|
||
|
|
"trainable_token_indices": null,
|
||
|
|
"use_dora": false,
|
||
|
|
"use_qalora": false,
|
||
|
|
"use_rslora": true
|
||
|
|
}
|