Sentence Similarity
sentence-transformers
PyTorch
ONNX
Safetensors
Transformers
Transformers.js
English
nomic_bert
feature-extraction
mteb
custom_code
Eval Results (legacy)
text-embeddings-inference
Instructions to use Karmukilan/nomic-embed-text-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Karmukilan/nomic-embed-text-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Karmukilan/nomic-embed-text-v1", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use Karmukilan/nomic-embed-text-v1 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Karmukilan/nomic-embed-text-v1", trust_remote_code=True) model = AutoModel.from_pretrained("Karmukilan/nomic-embed-text-v1", trust_remote_code=True) - Transformers.js
How to use Karmukilan/nomic-embed-text-v1 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'Karmukilan/nomic-embed-text-v1'); - Notebooks
- Google Colab
- Kaggle
| { | |
| "activation_function": "swiglu", | |
| "architectures": ["NomicBertModel"], | |
| "attn_pdrop": 0.0, | |
| "attention_probs_dropout_prob": 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" | |
| }, | |
| "bos_token_id": null, | |
| "causal": false, | |
| "classifier_dropout": null, | |
| "dense_seq_output": true, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": null, | |
| "fused_bias_fc": true, | |
| "fused_dropout_add_ln": true, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_epsilon": 1e-12, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 8192, | |
| "mlp_fc1_bias": false, | |
| "mlp_fc2_bias": false, | |
| "model_type": "nomic_bert", | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_inner": 3072, | |
| "n_layer": 12, | |
| "n_positions": 8192, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pad_vocab_size_multiple": 64, | |
| "parallel_block": false, | |
| "parallel_block_tied_norm": false, | |
| "prenorm": false, | |
| "qkv_proj_bias": false, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.0, | |
| "rope_parameters": { | |
| "rope_theta": 1000.0, | |
| "rope_type": "dynamic", | |
| "factor": 2.0 | |
| }, | |
| "rotary_emb_base": 1000, | |
| "rotary_emb_fraction": 1.0, | |
| "rotary_emb_interleaved": false, | |
| "rotary_emb_scale_base": null, | |
| "rotary_scaling_factor": 2, | |
| "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": "5.3.0.dev0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "use_flash_attn": true, | |
| "use_rms_norm": false, | |
| "use_xentropy": true, | |
| "vocab_size": 30528 | |
| } | |