survoltli's picture
peft weights of deepseek-coder 6.7b & clean log
97ec245
raw
history blame contribute delete
477 Bytes
{
"auto_mapping": null,
"base_model_name_or_path": "/c21071/lgc/llmpeft4apr/models/deepseek-coder-6.7b-base",
"encoder_dropout": 0.0,
"encoder_hidden_size": 2048,
"encoder_num_layers": 2,
"encoder_reparameterization_type": "MLP",
"inference_mode": true,
"num_attention_heads": 32,
"num_layers": 32,
"num_transformer_submodules": 1,
"num_virtual_tokens": 100,
"peft_type": "P_TUNING",
"revision": null,
"task_type": "CAUSAL_LM",
"token_dim": 4096
}