75 lines
2.4 KiB
JSON
75 lines
2.4 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "nomic-ai/nomic-xlm-2048",
|
||
|
|
"activation_function": "gelu",
|
||
|
|
"add_pooling_layer": false,
|
||
|
|
"architectures": [
|
||
|
|
"NomicBertModel"
|
||
|
|
],
|
||
|
|
"attn_pdrop": 0.0,
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",
|
||
|
|
"AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
|
||
|
|
"AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining",
|
||
|
|
"AutoModelForMultipleChoice": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForMultipleChoice",
|
||
|
|
"AutoModelForQuestionAnswering": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForQuestionAnswering",
|
||
|
|
"AutoModelForSequenceClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForSequenceClassification",
|
||
|
|
"AutoModelForTokenClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForTokenClassification"
|
||
|
|
},
|
||
|
|
"bos_token_id": null,
|
||
|
|
"causal": false,
|
||
|
|
"dense_seq_output": true,
|
||
|
|
"embd_pdrop": 0.1,
|
||
|
|
"eos_token_id": null,
|
||
|
|
"expert_choice_router": false,
|
||
|
|
"ffn_div": 1,
|
||
|
|
"fused_bias_fc": true,
|
||
|
|
"fused_dropout_add_ln": true,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"layer_norm_epsilon": 1e-05,
|
||
|
|
"max_trained_positions": 2048,
|
||
|
|
"mlp_fc1_bias": true,
|
||
|
|
"mlp_fc2_bias": true,
|
||
|
|
"model_type": "nomic_bert",
|
||
|
|
"moe_every_n_layers": 2,
|
||
|
|
"moe_impl": "megablocks",
|
||
|
|
"moe_normalize_expert_weights": false,
|
||
|
|
"moe_resid_pdrop": 0.0,
|
||
|
|
"moe_top_k": 2,
|
||
|
|
"n_embd": 768,
|
||
|
|
"n_head": 12,
|
||
|
|
"n_inner": 3072,
|
||
|
|
"n_layer": 12,
|
||
|
|
"n_positions": 2048,
|
||
|
|
"num_experts": 8,
|
||
|
|
"num_shared_experts": 0,
|
||
|
|
"pad_token_id": 1,
|
||
|
|
"pad_vocab_size_multiple": 64,
|
||
|
|
"parallel_block": false,
|
||
|
|
"parallel_block_tied_norm": false,
|
||
|
|
"prenorm": false,
|
||
|
|
"qkv_proj_bias": true,
|
||
|
|
"reorder_and_upcast_attn": false,
|
||
|
|
"resid_pdrop": 0.0,
|
||
|
|
"rotary_emb_base": 10000,
|
||
|
|
"rotary_emb_fraction": 1.0,
|
||
|
|
"rotary_emb_interleaved": false,
|
||
|
|
"rotary_emb_scale_base": null,
|
||
|
|
"rotary_scaling_factor": null,
|
||
|
|
"router_aux_loss_coef": 0.1,
|
||
|
|
"scale_attn_by_inverse_layer_idx": false,
|
||
|
|
"scale_attn_weights": true,
|
||
|
|
"summary_activation": null,
|
||
|
|
"summary_first_dropout": 0.1,
|
||
|
|
"summary_proj_to_labels": true,
|
||
|
|
"summary_type": "cls_index",
|
||
|
|
"summary_use_proj": true,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.44.2",
|
||
|
|
"type_vocab_size": 1,
|
||
|
|
"use_cache": true,
|
||
|
|
"use_flash_attn": true,
|
||
|
|
"use_rms_norm": null,
|
||
|
|
"use_xentropy": true,
|
||
|
|
"vocab_size": 250048
|
||
|
|
}
|