cola_vae/config.json

{
  "act": "swiglu",
  "architectures": [
    "ColaTextVAEModel"
  ],
  "attn_dropout": 0.0,
  "bias": true,
  "block_causal": true,
  "block_size": 1,
  "causal": false,
  "clip_qkv": null,
  "decoder_num_blocks": 4,
  "dim": 1536,
  "dropout": 0.0,
  "encoder_last_ln": true,
  "encoder_num_blocks": 4,
  "ffn_dim": 6144,
  "init_cutoff_factor": 3,
  "init_fn": "normal",
  "init_std": 0.02,
  "latent_dim": 16,
  "layer_norm_affine": true,
  "layer_norm_eps": 1e-06,
  "layer_norm_type": "layer_norm",
  "model_type": "cola_text_vae",
  "num_heads": 12,
  "patch_size": 1,
  "post_norm": true,
  "qk_bias": false,
  "qk_norm": true,
  "qk_norm_affine": true,
  "rope_full_precision": true,
  "rope_theta": 500000,
  "scaling_factor": 1.0,
  "shared_heads_kv": 1,
  "shifting_factor": 0.0,
  "torch_dtype": "float32",
  "transformers_version": "4.46.1",
  "use_emb": true,
  "use_variation": true,
  "vocab_size": 100278
}