CoolFace
Modelpublic

bumblebee-testing/tiny-random-NomicBertModel

sourceHugging Faceupdated 9mo agoView on Hugging Face
0likes165downloads
config.json62 linesDownload Raw Back to root
1{2  "activation_function": "swiglu",3  "architectures": [4    "NomicBertModel"5  ],6  "attn_pdrop": 0.0,7  "auto_map": {8    "AutoConfig": "configuration_hf_nomic_bert.NomicBertConfig",9    "AutoModel": "modeling_hf_nomic_bert.NomicBertModel",10    "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining",11    "AutoModelForMultipleChoice": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForMultipleChoice",12    "AutoModelForQuestionAnswering": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForQuestionAnswering",13    "AutoModelForSequenceClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForSequenceClassification",14    "AutoModelForTokenClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForTokenClassification"15  },16  "bos_token_id": null,17  "causal": false,18  "dense_seq_output": true,19  "dtype": "float32",20  "embd_pdrop": 0.0,21  "eos_token_id": null,22  "fused_bias_fc": true,23  "fused_dropout_add_ln": true,24  "initializer_range": 0.02,25  "layer_norm_epsilon": 1e-12,26  "max_trained_positions": 2048,27  "mlp_fc1_bias": false,28  "mlp_fc2_bias": false,29  "model_type": "nomic_bert",30  "n_embd": 32,31  "n_head": 4,32  "n_inner": 37,33  "n_layer": 2,34  "n_positions": 512,35  "pad_vocab_size_multiple": 64,36  "parallel_block": false,37  "parallel_block_tied_norm": false,38  "prenorm": false,39  "qkv_proj_bias": false,40  "reorder_and_upcast_attn": false,41  "resid_pdrop": 0.0,42  "rotary_emb_base": 1000,43  "rotary_emb_fraction": 1.0,44  "rotary_emb_interleaved": false,45  "rotary_emb_scale_base": null,46  "rotary_scaling_factor": null,47  "scale_attn_by_inverse_layer_idx": false,48  "scale_attn_weights": true,49  "summary_activation": null,50  "summary_first_dropout": 0.0,51  "summary_proj_to_labels": true,52  "summary_type": "cls_index",53  "summary_use_proj": true,54  "transformers_version": "4.57.0",55  "type_vocab_size": 2,56  "use_cache": true,57  "use_flash_attn": true,58  "use_rms_norm": false,59  "use_xentropy": true,60  "vocab_size": 102461}62