Flan-T5-large-wsc-PaFi-10-lora / adapter_config.json
Speeeed's picture
Upload model
660544b verified
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "google/flan-t5-large",
"bias": "none",
"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": 32,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"encoder.block.23.layer.0.SelfAttention.q",
"encoder.block.21.layer.0.SelfAttention.q",
"decoder.block.2.layer.0.SelfAttention.q",
"decoder.block.1.layer.0.SelfAttention.q",
"decoder.block.5.layer.0.SelfAttention.q",
"encoder.block.22.layer.0.SelfAttention.q",
"decoder.block.0.layer.0.SelfAttention.q",
"decoder.block.6.layer.1.EncDecAttention.q",
"decoder.block.2.layer.1.EncDecAttention.q",
"decoder.block.4.layer.0.SelfAttention.q",
"decoder.block.4.layer.1.EncDecAttention.q",
"decoder.block.1.layer.1.EncDecAttention.q",
"decoder.block.3.layer.0.SelfAttention.q",
"decoder.block.5.layer.1.EncDecAttention.q"
],
"task_type": "SEQ_2_SEQ_LM",
"use_dora": false,
"use_rslora": false
}