deepseek-7b-26k-lora-feb13 / adapter_config.json
zzz99's picture
Training in progress, epoch 0
44826e5 verified
raw
history blame contribute delete
710 Bytes
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_dropout": 0.1,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"lm_head",
"q_proj",
"down_proj",
"k_proj",
"o_proj",
"gate_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}