jamie8johnson/CodeRankEmbed-onnx
1644
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 },11 "bos_token_id": null,12 "causal": false,13 "dense_seq_output": true,14 "dtype": "float32",15 "embd_pdrop": 0.1,16 "eos_token_id": null,17 "export_model_type": "transformer",18 "fused_bias_fc": true,19 "fused_dropout_add_ln": true,20 "initializer_range": 0.02,21 "layer_norm_epsilon": 1e-12,22 "max_trained_positions": 2048,23 "mlp_fc1_bias": false,24 "mlp_fc2_bias": false,25 "model_type": "nomic_bert",26 "n_embd": 768,27 "n_head": 12,28 "n_inner": 3072,29 "n_layer": 12,30 "n_positions": 8192,31 "pad_vocab_size_multiple": 64,32 "parallel_block": false,33 "parallel_block_tied_norm": false,34 "prenorm": false,35 "qkv_proj_bias": false,36 "reorder_and_upcast_attn": false,37 "resid_pdrop": 0.1,38 "rotary_emb_base": 1000,39 "rotary_emb_fraction": 1.0,40 "rotary_emb_interleaved": false,41 "rotary_emb_scale_base": null,42 "rotary_scaling_factor": null,43 "scale_attn_by_inverse_layer_idx": false,44 "scale_attn_weights": true,45 "summary_activation": null,46 "summary_first_dropout": 0.1,47 "summary_proj_to_labels": true,48 "summary_type": "cls_index",49 "summary_use_proj": true,50 "transformers_version": "4.56.2",51 "type_vocab_size": 2,52 "use_cache": true,53 "use_flash_attn": true,54 "use_rms_norm": false,55 "use_xentropy": true,56 "vocab_size": 3052857}58 