MIMIR-1 / transformers /config.json
ainouche-abderahmane's picture
Upload folder using huggingface_hub
adb23bc verified
Raw History Blame Contribute Delete
2.3 kB
{
"architectures": [
"MimirModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_mimir.MimirConfig",
"AutoModel": "modeling_mimir.MimirModel"
},
"bos_token_id": 50281,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "cls",
"cls_token_id": 50281,
"decoder_bias": true,
"deterministic_flash_attn": false,
"dtype": "float32",
"embedding_dropout": 0.0,
"encoder_layers": 28,
"encoder_width": 1024,
"eos_token_id": 50282,
"feedforward_hidden": 1408,
"global_attn_every_n_layers": 3,
"head_size": 64,
"hidden_activation": "gelu",
"hidden_size": 1024,
"histogram_bins": 64,
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 2624,
"iterations": 4,
"latents": 32,
"layer_types": [
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"local_attention": 128,
"max_position_embeddings": 8192,
"mlp_bias": false,
"mlp_dropout": 0.0,
"model_type": "mimir",
"norm_bias": false,
"norm_eps": 1e-05,
"num_attention_heads": 16,
"num_hidden_layers": 28,
"pad_token_id": 50283,
"question_cap": 256,
"rope_parameters": {
"full_attention": {
"rope_theta": 160000.0,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sep_token_id": 50282,
"slots": 4,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"tie_word_embeddings": false,
"trained_layers": 14,
"transformers_version": "5.17.0",
"value_bins": 64,
"vocab_size": 50368,
"width": 512
}