AAMRA_2560T_LLAMA_3p1_8B-V2 / adapter_config.json
gjonesQ02's picture
Training in progress, epoch 0
d7fbd51 verified
raw
history blame contribute delete
743 Bytes
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-70B-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": 128,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 256,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"up_proj",
"o_proj",
"q_proj",
"down_proj",
"k_proj",
"v_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}