Text Generation
Transformers
PyTorch
xglm
xglm-2.9B / config.json
valhalla's picture
add model
7e60fee
raw
history blame
548 Bytes
{
"activation_dropout": 0.0,
"activation_function": "gelu",
"architectures": [
"XGLMForCausalLM"
],
"attention_dropout": 0.1,
"attention_heads": 16,
"bos_token_id": 0,
"d_model": 2048,
"decoder_start_token_id": 2,
"dropout": 0.1,
"eos_token_id": 2,
"ffn_dim": 8192,
"init_std": 0.02,
"layerdrop": 0.0,
"max_position_embeddings": 2048,
"model_type": "xglm",
"num_layers": 48,
"pad_token_id": 1,
"scale_embedding": true,
"transformers_version": "4.16.0.dev0",
"use_cache": true,
"vocab_size": 256008
}