CodeIsAbstract's picture
Training in progress, step 1000
6a1844d verified
Raw
History Blame Contribute Delete
604 Bytes
{
"architectures": [
"HybridTimeScaleLM"
],
"bos_token_id": 1,
"chunk_size": 128,
"dropout": 0.05,
"dtype": "float32",
"eos_token_id": 2,
"latent_dim": 768,
"layer_types": [
"linear",
"linear",
"linear",
"softmax",
"linear",
"linear",
"linear",
"softmax",
"linear",
"linear",
"linear",
"softmax"
],
"model_type": "hybrid_fourier_lm",
"num_layers": 12,
"num_modes": 64,
"pad_token_id": 2,
"tie_word_embeddings": true,
"time_scale": 128.0,
"transformers_version": "5.14.1",
"use_cache": false,
"vocab_size": 32768
}