tsss1/expressvpn_embeddingmodel
021
1{2 "_name_or_path": "nomic-ai/nomic-embed-text-v2-moe",3 "activation_function": "gelu",4 "add_pooling_layer": false,5 "architectures": [6 "NomicBertModel"7 ],8 "attn_pdrop": 0.0,9 "auto_map": {10 "AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",11 "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",12 "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining",13 "AutoModelForMultipleChoice": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForMultipleChoice",14 "AutoModelForQuestionAnswering": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForQuestionAnswering",15 "AutoModelForSequenceClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForSequenceClassification",16 "AutoModelForTokenClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForTokenClassification"17 },18 "bos_token_id": null,19 "causal": false,20 "dense_seq_output": true,21 "embd_pdrop": 0.1,22 "eos_token_id": null,23 "expert_choice_router": false,24 "ffn_div": 1,25 "fused_bias_fc": true,26 "fused_dropout_add_ln": true,27 "initializer_range": 0.02,28 "layer_norm_epsilon": 1e-05,29 "max_trained_positions": 2048,30 "mlp_fc1_bias": true,31 "mlp_fc2_bias": true,32 "model_type": "nomic_bert",33 "moe_every_n_layers": 2,34 "moe_impl": "megablocks",35 "moe_normalize_expert_weights": false,36 "moe_resid_pdrop": 0.0,37 "moe_top_k": 2,38 "n_embd": 768,39 "n_head": 12,40 "n_inner": 3072,41 "n_layer": 12,42 "n_positions": 2048,43 "num_experts": 8,44 "num_shared_experts": 0,45 "pad_token_id": 1,46 "pad_vocab_size_multiple": 64,47 "parallel_block": false,48 "parallel_block_tied_norm": false,49 "prenorm": false,50 "qkv_proj_bias": true,51 "reorder_and_upcast_attn": false,52 "resid_pdrop": 0.0,53 "rotary_emb_base": 10000,54 "rotary_emb_fraction": 1.0,55 "rotary_emb_interleaved": false,56 "rotary_emb_scale_base": null,57 "rotary_scaling_factor": null,58 "router_aux_loss_coef": 0.1,59 "scale_attn_by_inverse_layer_idx": false,60 "scale_attn_weights": true,61 "summary_activation": null,62 "summary_first_dropout": 0.1,63 "summary_proj_to_labels": true,64 "summary_type": "cls_index",65 "summary_use_proj": true,66 "torch_dtype": "float32",67 "transformers_version": "4.48.3",68 "type_vocab_size": 1,69 "use_cache": true,70 "use_flash_attn": true,71 "use_rms_norm": null,72 "use_xentropy": true,73 "vocab_size": 25004874}75 