KenT-300M-Base / config.json
KenteaKe11
KenT-300M: EMA memory with learned per-layer alpha, 1 WNN per layer, 24 layers
99eb3d1
Raw History Blame Contribute Delete
669 Bytes
{
"model_type": "kent",
"architectures": [
"KentForCausalLM"
],
"auto_map": {
"AutoConfig": "model.KentConfig",
"AutoModel": "model.KentModel",
"AutoModelForCausalLM": "model.KentForCausalLM"
},
"vocab_size": 50257,
"hidden_size": 512,
"num_hidden_layers": 24,
"resolution_size": 8,
"feature_dim": 512,
"intermediate_size": 2048,
"rms_norm_eps": 1e-05,
"use_bias": true,
"initializer_range": 0.02,
"use_cache": true,
"tie_word_embeddings": true,
"pad_token_id": 50256,
"bos_token_id": 50256,
"eos_token_id": 50256,
"dtype": "float16",
"ema_alpha_first": 0.5,
"ema_alpha_last": 0.01,
"ema_block_size": 128
}