paligemma-hindi-part-2 / adapter_config.json
damerajee's picture
Training in progress, step 20
de570c8 verified
raw
history blame
694 Bytes
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "google/paligemma-3b-pt-224",
"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": 32,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": [
"lm_head"
],
"peft_type": "LORA",
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"o_proj",
"v_proj",
"q_proj",
"k_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": true
}