ReMamba / adapter_config.json
lblankl's picture
Add LoRA weight of ReMamba-hf
ad09676 verified
raw
history blame contribute delete
768 Bytes
{
"alpha_pattern": {},
"auto_mapping": {
"base_model_class": "ReMambaForCausalLM",
"parent_library": "src.model.ReMamba"
},
"base_model_name_or_path": "state-spaces/mamba-2.8b-hf",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 8,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": [
"Q_proj",
"V_proj",
"K_proj",
"ret_bias",
"dt_proj"
],
"peft_type": "LORA",
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"out_proj",
"in_proj",
"embeddings",
"lm_head"
],
"task_type": null
}