102 lines
3.3 KiB
JSON
102 lines
3.3 KiB
JSON
|
{
|
||
|
|
"alpha_pattern": {},
|
||
|
|
"auto_mapping": {
|
||
|
|
"base_model_class": "LlamaForCausalLM",
|
||
|
|
"parent_library": "transformers.models.llama.modeling_llama",
|
||
|
|
"unsloth_fixed": true
|
||
|
|
},
|
||
|
|
"base_model_name_or_path": "unsloth/Llama-3.2-3B-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": 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": [
|
||
|
|
"model.layers.16.mlp.up_proj",
|
||
|
|
"model.layers.18.mlp.gate_proj",
|
||
|
|
"model.layers.20.self_attn.q_proj",
|
||
|
|
"model.layers.17.self_attn.o_proj",
|
||
|
|
"model.layers.20.self_attn.o_proj",
|
||
|
|
"model.layers.19.mlp.down_proj",
|
||
|
|
"model.layers.16.mlp.down_proj",
|
||
|
|
"model.layers.21.mlp.gate_proj",
|
||
|
|
"model.layers.23.self_attn.v_proj",
|
||
|
|
"model.layers.24.self_attn.k_proj",
|
||
|
|
"model.layers.24.mlp.gate_proj",
|
||
|
|
"model.layers.17.self_attn.k_proj",
|
||
|
|
"model.layers.17.self_attn.v_proj",
|
||
|
|
"model.layers.18.mlp.down_proj",
|
||
|
|
"model.layers.24.mlp.down_proj",
|
||
|
|
"model.layers.22.self_attn.v_proj",
|
||
|
|
"model.layers.19.self_attn.q_proj",
|
||
|
|
"model.layers.22.mlp.down_proj",
|
||
|
|
"model.layers.16.self_attn.q_proj",
|
||
|
|
"model.layers.19.self_attn.k_proj",
|
||
|
|
"model.layers.17.mlp.gate_proj",
|
||
|
|
"model.layers.21.self_attn.k_proj",
|
||
|
|
"model.layers.17.self_attn.q_proj",
|
||
|
|
"model.layers.23.mlp.down_proj",
|
||
|
|
"model.layers.21.self_attn.o_proj",
|
||
|
|
"model.layers.18.self_attn.v_proj",
|
||
|
|
"model.layers.22.self_attn.o_proj",
|
||
|
|
"model.layers.17.mlp.down_proj",
|
||
|
|
"model.layers.21.self_attn.q_proj",
|
||
|
|
"model.layers.16.self_attn.v_proj",
|
||
|
|
"model.layers.22.mlp.gate_proj",
|
||
|
|
"model.layers.18.self_attn.k_proj",
|
||
|
|
"model.layers.19.mlp.gate_proj",
|
||
|
|
"model.layers.20.self_attn.k_proj",
|
||
|
|
"model.layers.23.self_attn.o_proj",
|
||
|
|
"model.layers.23.mlp.up_proj",
|
||
|
|
"model.layers.18.self_attn.o_proj",
|
||
|
|
"model.layers.21.mlp.up_proj",
|
||
|
|
"model.layers.16.self_attn.k_proj",
|
||
|
|
"model.layers.20.mlp.gate_proj",
|
||
|
|
"model.layers.18.self_attn.q_proj",
|
||
|
|
"model.layers.20.mlp.up_proj",
|
||
|
|
"model.layers.24.self_attn.q_proj",
|
||
|
|
"model.layers.24.self_attn.v_proj",
|
||
|
|
"model.layers.24.self_attn.o_proj",
|
||
|
|
"model.layers.22.mlp.up_proj",
|
||
|
|
"model.layers.23.mlp.gate_proj",
|
||
|
|
"model.layers.23.self_attn.q_proj",
|
||
|
|
"model.layers.19.mlp.up_proj",
|
||
|
|
"model.layers.17.mlp.up_proj",
|
||
|
|
"model.layers.20.mlp.down_proj",
|
||
|
|
"model.layers.19.self_attn.o_proj",
|
||
|
|
"model.layers.19.self_attn.v_proj",
|
||
|
|
"model.layers.22.self_attn.k_proj",
|
||
|
|
"model.layers.18.mlp.up_proj",
|
||
|
|
"model.layers.24.mlp.up_proj",
|
||
|
|
"model.layers.23.self_attn.k_proj",
|
||
|
|
"model.layers.16.self_attn.o_proj",
|
||
|
|
"model.layers.21.mlp.down_proj",
|
||
|
|
"model.layers.21.self_attn.v_proj",
|
||
|
|
"model.layers.22.self_attn.q_proj",
|
||
|
|
"model.layers.16.mlp.gate_proj",
|
||
|
|
"model.layers.20.self_attn.v_proj"
|
||
|
|
],
|
||
|
|
"target_parameters": null,
|
||
|
|
"task_type": "CAUSAL_LM",
|
||
|
|
"trainable_token_indices": null,
|
||
|
|
"use_dora": false,
|
||
|
|
"use_qalora": false,
|
||
|
|
"use_rslora": true
|
||
|
|
}
|