laya / config.json
AlazarM's picture
Add verified MLX Laya checkpoint
625d295 verified
Raw History Blame Contribute Delete
3.72 kB
{
"decision_config": {
"encoder": "answerdotai/ModernBERT-large",
"head_layers": 2,
"max_len": 512,
"head_max_len": 192,
"max_prefixes": 6,
"act_costs": {
"escalate": 0.5
},
"cost_wrong_act": 3.0,
"amp_dtype": "bf16",
"model_name": "rl-agent",
"temperature": [
1.6369030475616455,
1.2514300346374512,
1.983399510383606
],
"temperature_by_options": {
"choice:3-5": 1.7601518630981445,
"choice:6-10": 1.0000158548355103,
"score:3-5": 1.2514300346374512,
"noul:2": 1.983399510383606,
"choice:11+": 0.10058280825614929,
"choice:2": 1.9063563346862793
},
"training": {
"updates": 7313,
"epochs_completed": 1,
"hours": 1.96,
"world_size": 1,
"fine_tuned_from_checkpoint": true
}
},
"encoder_config": {
"architectures": [
"ModernBertForMaskedLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50281,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "mean",
"cls_token_id": 50281,
"decoder_bias": true,
"deterministic_flash_attn": false,
"dtype": "float32",
"embedding_dropout": 0.0,
"eos_token_id": 50282,
"global_attn_every_n_layers": 3,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 1024,
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 2624,
"layer_norm_eps": 1e-05,
"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": "modernbert",
"norm_bias": false,
"norm_eps": 1e-05,
"num_attention_heads": 16,
"num_hidden_layers": 28,
"pad_token_id": 50283,
"position_embedding_type": "absolute",
"repad_logits_with_grad": false,
"rope_parameters": {
"full_attention": {
"rope_theta": 160000.0,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sep_token_id": 50282,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"tie_word_embeddings": true,
"transformers_version": "5.0.0",
"vocab_size": 50368
},
"head_layers": 2,
"model_type": "laya"
}