mmBERT fresh-head config + full 4K decision data

This commit is contained in:
dingbin.wang 2026-10-21 17:12:19 +08:00
parent d9cb063aa4
commit e94dbb638b
4 changed files with 251607 additions and 0 deletions

View File

@ -0,0 +1,84 @@
{
"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
}

View File

@ -0,0 +1,11 @@
{
"encoder": "/tmp/base",
"head_layers": 2,
"max_len": 512,
"head_max_len": 192,
"max_prefixes": 6,
"act_costs": {},
"cost_wrong_act": 3.0,
"amp_dtype": "bf16",
"model_name": "laya-mmbert-fromscratch"
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,14 @@
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 8192,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}