llama-3.1-8B-instruct-gsm8k / adapter_config.json
ketchup123's picture
Training in progress, step 42
ea45cf7 verified
raw
history blame
760 Bytes
{
"alpha_pattern": {},
"auto_mapping": {
"base_model_class": "LlamaForCausalLM",
"parent_library": "transformers.models.llama.modeling_llama"
},
"base_model_name_or_path": "meta-llama/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": 0.1,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"v_proj",
"q_proj"
],
"task_type": null,
"use_dora": false,
"use_rslora": false
}