spam-llama3.1-8B-teacher-a / adapter_config.json
arshiakarimian1's picture
Training in progress, step 209
8354e72 verified
raw
history blame contribute delete
No virus
795 Bytes
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"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": 16,
"lora_dropout": 0.25,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"model.layers.30.self_attn.v_proj",
"model.layers.31.self_attn.k_proj",
"model.layers.31.self_attn.v_proj",
"model.layers.30.self_attn.k_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}