23 lines
600 B
JSON
23 lines
600 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"AILOForCausalLM"
|
||
|
|
],
|
||
|
|
"model_type": "ailo",
|
||
|
|
"vocab_size": 50257,
|
||
|
|
"hidden_size": 768,
|
||
|
|
"num_hidden_layers": 12,
|
||
|
|
"num_attention_heads": 12,
|
||
|
|
"intermediate_size": 3072,
|
||
|
|
"max_position_embeddings": 512,
|
||
|
|
"hidden_dropout_prob": 0.1,
|
||
|
|
"attention_probs_dropout_prob": 0.1,
|
||
|
|
"bos_token_id": 50256,
|
||
|
|
"eos_token_id": 50256,
|
||
|
|
"pad_token_id": 50256,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.57.0",
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "configuration_ailo.AILOConfig",
|
||
|
|
"AutoModelForCausalLM": "modeling_ailo.AILOForCausalLM"
|
||
|
|
}
|
||
|
|
}
|