guruofguru_13b_instr / adapter_config.json
jazzwezz's picture
Initial commit- v1 codellama 13b instruct trained on 2 epochs 2x1029 samples. 2 epochs lr const 7e-05 warmup 0.03
6f44b8d
raw
history blame contribute delete
739 Bytes
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
"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": 256,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"v_proj",
"k_proj",
"gate_proj",
"down_proj",
"o_proj",
"up_proj",
"q_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}