| { |
| "architecture": "interleaved", |
| "architectures": [ |
| "TextLMModel" |
| ], |
| "assistant_offset": 8192, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_output_gate": true, |
| "blank_loss_weight": 0.1, |
| "blank_token_id": 248077, |
| "bos_token_id": null, |
| "cross_attention_causal": true, |
| "decoder_num_hidden_layers": null, |
| "dtype": "float32", |
| "encoder_num_hidden_layers": null, |
| "eos_token_id": 248044, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 3584, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 16, |
| "linear_value_head_dim": 128, |
| "mamba_ssm_dtype": "float32", |
| "mask_prob": 0.0, |
| "mask_token_id": 248081, |
| "max_position_embeddings": 4194304, |
| "mlp_only_layers": [], |
| "model_type": "text_lm", |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 8, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 2, |
| "onset_loss_weight": 0.0, |
| "onset_positive_weight": 20.0, |
| "pad_token_id": null, |
| "partial_rotary_factor": 0.25, |
| "random_prob": 0.0, |
| "random_token_vocab_size": null, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 10000000, |
| "rope_type": "default" |
| }, |
| "shift_smear_eps": 0.1, |
| "shift_tolerance": 2, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.16.1", |
| "use_cache": false, |
| "user_loss_weight": 1.0, |
| "vocab_size": 248320 |
| } |
|
|
