big_kto1 / adapter_config.json
stojchet's picture
Training in progress, step 500
fdb84ab verified
raw
history blame
842 Bytes
{
"alpha_pattern": {},
"auto_mapping": {
"base_model_class": "LlamaForCausalLM",
"parent_library": "transformers.models.llama.modeling_llama"
},
"base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
"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": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"down_proj",
"k_proj",
"v_proj",
"up_proj",
"q_proj"
],
"task_type": null,
"use_dora": false,
"use_rslora": false
}