35 lines
873 B
JSON
35 lines
873 B
JSON
{
|
|
"base_model": "meta-llama/Llama-3.2-1B",
|
|
"hidden_size": 2048,
|
|
"ffn_hidden": 4096,
|
|
"lora_r": 16,
|
|
"lora_alpha": 32,
|
|
"lora_dropout": 0.05,
|
|
"lora_targets": [
|
|
"q_proj",
|
|
"v_proj",
|
|
"k_proj",
|
|
"o_proj"
|
|
],
|
|
"num_experts": 4,
|
|
"top_k": 2,
|
|
"dataset_name": "Malikeh1375/medical-question-answering-datasets",
|
|
"dataset_subset": "all-processed",
|
|
"num_samples": 15000,
|
|
"max_length": 256,
|
|
"batch_size": 2,
|
|
"grad_accum": 16,
|
|
"warmup_ratio": 0.1,
|
|
"val_split": 0.1,
|
|
"save_path": "/kaggle/working/llama_moe_medical",
|
|
"model_type": "llama-3.2-1b-lora-moe",
|
|
"lora_merged": true,
|
|
"hf_username": "saadxsalman",
|
|
"repo_id": "saadxsalman/ss-medical-moe",
|
|
"domain_experts": {
|
|
"expert_1": "Symptoms & Diagnosis",
|
|
"expert_2": "Drug Interactions",
|
|
"expert_3": "Anatomy & Physiology",
|
|
"expert_4": "Treatment & Procedures"
|
|
}
|
|
} |