tarekxpc's picture
Training in progress, step 3000
b8b1761 verified
raw
history blame
190 Bytes
{"d_model": 768, "n_layer": 24, "vocab_size": 50277, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 8, "tie_embeddings": false}