csqa-gpt2-large-ctx-c / decoder_model /adapter_config.json
hbin0701's picture
Add CSQA GPT2-large context-aware model
4859eec
raw
history blame contribute delete
607 Bytes
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/mnt/nas/hyeonbin/LS_MODELS/csqa/sft/csqa_gpt2-large/checkpoint-255",
"bias": "none",
"fan_in_fan_out": true,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 1024,
"lora_dropout": 0.1,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 256,
"rank_pattern": {},
"revision": null,
"target_modules": [
"c_attn"
],
"task_type": "CAUSAL_LM"
}