qm-pythia-2.8b-mixture / adapter_config.json
atmallen's picture
Training in progress, step 4000
0472fc1
raw
history blame
635 Bytes
{
"alpha_pattern": {},
"auto_mapping": {
"base_model_class": "GPTNeoXForCausalLM",
"parent_library": "transformers.models.gpt_neox.modeling_gpt_neox"
},
"base_model_name_or_path": "EleutherAI/pythia-2.8b",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"lora_alpha": 8,
"lora_dropout": 0.0,
"modules_to_save": null,
"peft_type": "LORA",
"r": 8,
"rank_pattern": {},
"revision": null,
"target_modules": [
"query_key_value",
"dense_h_to_4h",
"dense_4h_to_h"
],
"task_type": null
}