lsmille's picture
lsmille/lora_evo_ta_all_layers_18_attention_layers
ad2b85d verified
{
"alpha_pattern": {},
"auto_mapping": {
"base_model_class": "StripedHyenaModelForCausalLM",
"parent_library": "transformers_modules.togethercomputer.evo-1-131k-base.567369e9825aa08b3de4b122fca34fac6a890602.modeling_hyena"
},
"base_model_name_or_path": "togethercomputer/evo-1-8k-base",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": "gaussian",
"layer_replication": null,
"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": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"backbone.blocks.24.inner_mha_cls.out_proj",
"backbone.blocks.8.inner_mha_cls.Wqkv",
"backbone.blocks.8.inner_mha_cls.out_proj",
"backbone.blocks.16.inner_mha_cls.Wqkv",
"backbone.blocks.16.inner_mha_cls.out_proj",
"backbone.blocks.24.inner_mha_cls.Wqkv"
],
"task_type": null,
"use_dora": false,
"use_rslora": false
}