|
{ |
|
"alpha_pattern": {}, |
|
"auto_mapping": null, |
|
"base_model_name_or_path": "Steelskull/L3.3-Electra-R1-70b", |
|
"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": 0.05, |
|
"megatron_config": null, |
|
"megatron_core": "megatron.core", |
|
"modules_to_save": null, |
|
"peft_type": "LORA", |
|
"r": 8, |
|
"rank_pattern": {}, |
|
"revision": null, |
|
"target_modules": [ |
|
"model.layers.65.self_attn.v_proj", |
|
"model.layers.71.self_attn.v_proj", |
|
"model.layers.76.self_attn.k_proj", |
|
"model.layers.64.self_attn.q_proj", |
|
"model.layers.75.self_attn.q_proj", |
|
"model.layers.64.self_attn.o_proj", |
|
"model.layers.72.self_attn.v_proj", |
|
"model.layers.69.self_attn.o_proj", |
|
"model.layers.72.self_attn.o_proj", |
|
"model.layers.73.self_attn.v_proj", |
|
"model.layers.70.self_attn.v_proj", |
|
"model.layers.68.self_attn.q_proj", |
|
"model.layers.67.self_attn.o_proj", |
|
"model.layers.78.self_attn.v_proj", |
|
"model.layers.74.self_attn.o_proj", |
|
"model.layers.65.self_attn.k_proj", |
|
"model.layers.74.self_attn.v_proj", |
|
"model.layers.67.self_attn.k_proj", |
|
"model.layers.75.self_attn.v_proj", |
|
"model.layers.62.self_attn.q_proj", |
|
"model.layers.66.self_attn.q_proj", |
|
"model.layers.69.self_attn.v_proj", |
|
"model.layers.71.self_attn.q_proj", |
|
"model.layers.66.self_attn.o_proj", |
|
"model.layers.76.self_attn.q_proj", |
|
"model.layers.61.self_attn.q_proj", |
|
"model.layers.64.self_attn.v_proj", |
|
"model.layers.73.self_attn.o_proj", |
|
"model.layers.71.self_attn.o_proj", |
|
"model.layers.72.self_attn.q_proj", |
|
"model.layers.72.self_attn.k_proj", |
|
"model.layers.70.self_attn.q_proj", |
|
"model.layers.71.self_attn.k_proj", |
|
"model.layers.77.self_attn.q_proj", |
|
"model.layers.73.self_attn.k_proj", |
|
"model.layers.60.self_attn.v_proj", |
|
"model.layers.61.self_attn.o_proj", |
|
"model.layers.77.self_attn.k_proj", |
|
"model.layers.61.self_attn.k_proj", |
|
"model.layers.60.self_attn.o_proj", |
|
"model.layers.60.self_attn.q_proj", |
|
"model.layers.61.self_attn.v_proj", |
|
"model.layers.60.self_attn.k_proj", |
|
"model.layers.62.self_attn.k_proj", |
|
"model.layers.62.self_attn.v_proj", |
|
"model.layers.62.self_attn.o_proj", |
|
"model.layers.70.self_attn.o_proj", |
|
"model.layers.65.self_attn.o_proj", |
|
"model.layers.69.self_attn.k_proj", |
|
"model.layers.75.self_attn.k_proj", |
|
"model.layers.77.self_attn.o_proj", |
|
"model.layers.64.self_attn.k_proj", |
|
"model.layers.68.self_attn.v_proj", |
|
"model.layers.76.self_attn.v_proj", |
|
"model.layers.63.self_attn.q_proj", |
|
"model.layers.76.self_attn.o_proj", |
|
"model.layers.66.self_attn.v_proj", |
|
"model.layers.67.self_attn.v_proj", |
|
"model.layers.73.self_attn.q_proj", |
|
"model.layers.74.self_attn.q_proj", |
|
"model.layers.78.self_attn.q_proj", |
|
"model.layers.67.self_attn.q_proj", |
|
"model.layers.65.self_attn.q_proj", |
|
"model.layers.69.self_attn.q_proj", |
|
"model.layers.68.self_attn.k_proj", |
|
"model.layers.63.self_attn.o_proj", |
|
"model.layers.63.self_attn.v_proj", |
|
"model.layers.66.self_attn.k_proj", |
|
"model.layers.63.self_attn.k_proj", |
|
"model.layers.77.self_attn.v_proj", |
|
"model.layers.74.self_attn.k_proj", |
|
"model.layers.75.self_attn.o_proj", |
|
"model.layers.70.self_attn.k_proj", |
|
"model.layers.68.self_attn.o_proj", |
|
"model.layers.78.self_attn.o_proj", |
|
"model.layers.78.self_attn.k_proj" |
|
], |
|
"task_type": "CAUSAL_LM", |
|
"trainable_token_indices": null, |
|
"use_dora": false, |
|
"use_rslora": false |
|
} |