|
{ |
|
"architectures": [ |
|
"CoDALanguageModel" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"attention_kernel": "flash_attention", |
|
"auto_map": { |
|
"AutoConfig": "model_config.CoDAConfig", |
|
"AutoModel": "modeling_coda.CoDALanguageModel" |
|
}, |
|
"block_masking_probability": [ |
|
0.25, |
|
0.5, |
|
0.5, |
|
0.75, |
|
0.25 |
|
], |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 2048, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 6144, |
|
"mask_block_sizes": [ |
|
4, |
|
8, |
|
16, |
|
32 |
|
], |
|
"mask_token_id": 151669, |
|
"max_position_embeddings": 40960, |
|
"max_window_layers": 28, |
|
"model_type": "CoDA", |
|
"num_attention_heads": 16, |
|
"num_hidden_layers": 28, |
|
"num_key_value_heads": 8, |
|
"pad_token_id": 151643, |
|
"prefix_probability": 0, |
|
"rms_norm_eps": 1e-06, |
|
"rope_scaling": null, |
|
"rope_theta": 1000000, |
|
"sampling_eps": [ |
|
0.001, |
|
0.25, |
|
0.5, |
|
0.25, |
|
0.001 |
|
], |
|
"sliding_window": null, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.47.1", |
|
"truncate_probability": 0, |
|
"use_cache": true, |
|
"use_sliding_window": false, |
|
"vocab_size": 151936 |
|
} |
|
|