| { | |
| "ae_path": "/mnt/gemininjceph2/geminicephfs/pr-others-prctrans/chenzeshao/tfs_llm/calm_443/checkpoints/autoencoder_patch4_abl_d128_kl0001_long/checkpoint-30000", | |
| "architectures": [ | |
| "EnergyTransformer" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "beta": 1.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6880, | |
| "latent_size": 128, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "noise_size": 64, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 32, | |
| "num_mlp_layers": 4, | |
| "pad_token_id": 128256, | |
| "patch_size": 4, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "temp": 1.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.0", | |
| "use_cache": true, | |
| "vocab_size": 128257 | |
| } | |