AdwolfCzar's picture
checkpoint step2000
7b2ca89 verified
Raw
History Blame Contribute Delete
4.2 kB
{
"alora_invocation_tokens": null,
"alpha_pattern": {
"txtfusion.layerwise_blocks.0.attn.gate": 128,
"txtfusion.layerwise_blocks.0.attn.wk": 128,
"txtfusion.layerwise_blocks.0.attn.wo": 128,
"txtfusion.layerwise_blocks.0.attn.wq": 128,
"txtfusion.layerwise_blocks.0.attn.wv": 128,
"txtfusion.layerwise_blocks.0.mlp.down": 128,
"txtfusion.layerwise_blocks.0.mlp.gate": 128,
"txtfusion.layerwise_blocks.0.mlp.up": 128,
"txtfusion.layerwise_blocks.1.attn.gate": 128,
"txtfusion.layerwise_blocks.1.attn.wk": 128,
"txtfusion.layerwise_blocks.1.attn.wo": 128,
"txtfusion.layerwise_blocks.1.attn.wq": 128,
"txtfusion.layerwise_blocks.1.attn.wv": 128,
"txtfusion.layerwise_blocks.1.mlp.down": 128,
"txtfusion.layerwise_blocks.1.mlp.gate": 128,
"txtfusion.layerwise_blocks.1.mlp.up": 128,
"txtfusion.refiner_blocks.0.attn.gate": 128,
"txtfusion.refiner_blocks.0.attn.wk": 128,
"txtfusion.refiner_blocks.0.attn.wo": 128,
"txtfusion.refiner_blocks.0.attn.wq": 128,
"txtfusion.refiner_blocks.0.attn.wv": 128,
"txtfusion.refiner_blocks.0.mlp.down": 128,
"txtfusion.refiner_blocks.0.mlp.gate": 128,
"txtfusion.refiner_blocks.0.mlp.up": 128,
"txtfusion.refiner_blocks.1.attn.gate": 128,
"txtfusion.refiner_blocks.1.attn.wk": 128,
"txtfusion.refiner_blocks.1.attn.wo": 128,
"txtfusion.refiner_blocks.1.attn.wq": 128,
"txtfusion.refiner_blocks.1.attn.wv": 128,
"txtfusion.refiner_blocks.1.mlp.down": 128,
"txtfusion.refiner_blocks.1.mlp.gate": 128,
"txtfusion.refiner_blocks.1.mlp.up": 128
},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.0,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"monteclora_config": null,
"peft_type": "LORA",
"peft_version": "0.20.0",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {
"txtfusion.layerwise_blocks.0.attn.gate": 128,
"txtfusion.layerwise_blocks.0.attn.wk": 128,
"txtfusion.layerwise_blocks.0.attn.wo": 128,
"txtfusion.layerwise_blocks.0.attn.wq": 128,
"txtfusion.layerwise_blocks.0.attn.wv": 128,
"txtfusion.layerwise_blocks.0.mlp.down": 128,
"txtfusion.layerwise_blocks.0.mlp.gate": 128,
"txtfusion.layerwise_blocks.0.mlp.up": 128,
"txtfusion.layerwise_blocks.1.attn.gate": 128,
"txtfusion.layerwise_blocks.1.attn.wk": 128,
"txtfusion.layerwise_blocks.1.attn.wo": 128,
"txtfusion.layerwise_blocks.1.attn.wq": 128,
"txtfusion.layerwise_blocks.1.attn.wv": 128,
"txtfusion.layerwise_blocks.1.mlp.down": 128,
"txtfusion.layerwise_blocks.1.mlp.gate": 128,
"txtfusion.layerwise_blocks.1.mlp.up": 128,
"txtfusion.refiner_blocks.0.attn.gate": 128,
"txtfusion.refiner_blocks.0.attn.wk": 128,
"txtfusion.refiner_blocks.0.attn.wo": 128,
"txtfusion.refiner_blocks.0.attn.wq": 128,
"txtfusion.refiner_blocks.0.attn.wv": 128,
"txtfusion.refiner_blocks.0.mlp.down": 128,
"txtfusion.refiner_blocks.0.mlp.gate": 128,
"txtfusion.refiner_blocks.0.mlp.up": 128,
"txtfusion.refiner_blocks.1.attn.gate": 128,
"txtfusion.refiner_blocks.1.attn.wk": 128,
"txtfusion.refiner_blocks.1.attn.wo": 128,
"txtfusion.refiner_blocks.1.attn.wq": 128,
"txtfusion.refiner_blocks.1.attn.wv": 128,
"txtfusion.refiner_blocks.1.mlp.down": 128,
"txtfusion.refiner_blocks.1.mlp.gate": 128,
"txtfusion.refiner_blocks.1.mlp.up": 128
},
"revision": null,
"target_modules": [
"wv",
"down",
"up",
"gate",
"wk",
"wq",
"wo"
],
"target_parameters": null,
"task_type": null,
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false,
"velora_config": null
}