Feature Extraction
sentence-transformers
Safetensors
English
neobert
sparse-encoder
sparse
splade
Generated from Trainer
dataset_size:630000
loss:SpladeLoss
loss:SparseMultipleNegativesRankingLoss
loss:FlopsLoss
custom_code
Eval Results (legacy)
Instructions to use drexalt/splade-NeoBERT-msmarco-triplets-muon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use drexalt/splade-NeoBERT-msmarco-triplets-muon with sentence-transformers:
from sentence_transformers import SparseEncoder model = SparseEncoder("drexalt/splade-NeoBERT-msmarco-triplets-muon", trust_remote_code=True) queries = ["Which planet is known as the Red Planet?"] documents = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) - Notebooks
- Google Colab
- Kaggle
Download config.json from drexalt/splade-NeoBERT-msmarco-triplets-muon: direct link, hf CLI and curl.
- Browser
- Download file 2.92 kB
-
https://huggingface.co/drexalt/splade-NeoBERT-msmarco-triplets-muon/resolve/main/config.json
- Command line
-
hf download hf://drexalt/splade-NeoBERT-msmarco-triplets-muon/config.json
-
curl -L -o config.json https://huggingface.co/drexalt/splade-NeoBERT-msmarco-triplets-muon/resolve/main/config.json
2.92 kB
| { | |
| "architectures": [ | |
| "NeoBERTLMHead" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "model.NeoBERTConfig", | |
| "AutoModel": "model.NeoBERT", | |
| "AutoModelForMaskedLM": "model.NeoBERTLMHead", | |
| "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification" | |
| }, | |
| "classifier_init_range": 0.02, | |
| "decoder_init_range": 0.02, | |
| "dim_head": 64, | |
| "dtype": "float32", | |
| "embedding_init_range": 0.02, | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "kwargs": { | |
| "architectures": [ | |
| "NeoBERTLMHead" | |
| ], | |
| "attn_implementation": null, | |
| "auto_map": { | |
| "AutoConfig": "model.NeoBERTConfig", | |
| "AutoModel": "model.NeoBERT", | |
| "AutoModelForMaskedLM": "model.NeoBERTLMHead", | |
| "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification" | |
| }, | |
| "classifier_init_range": 0.02, | |
| "dim_head": 64, | |
| "dtype": "float32", | |
| "kwargs": { | |
| "architectures": [ | |
| "NeoBERTLMHead" | |
| ], | |
| "attn_implementation": null, | |
| "auto_map": { | |
| "AutoConfig": "model.NeoBERTConfig", | |
| "AutoModel": "model.NeoBERT", | |
| "AutoModelForMaskedLM": "model.NeoBERTLMHead", | |
| "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification" | |
| }, | |
| "classifier_init_range": 0.02, | |
| "dim_head": 64, | |
| "dtype": "float32", | |
| "kwargs": { | |
| "architectures": [ | |
| "NeoBERTLMHead" | |
| ], | |
| "attn_implementation": null, | |
| "auto_map": { | |
| "AutoConfig": "model.NeoBERTConfig", | |
| "AutoModel": "model.NeoBERT", | |
| "AutoModelForMaskedLM": "model.NeoBERTLMHead", | |
| "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification" | |
| }, | |
| "classifier_init_range": 0.02, | |
| "dim_head": 64, | |
| "kwargs": { | |
| "classifier_init_range": 0.02, | |
| "pretrained_model_name_or_path": "google-bert/bert-base-uncased", | |
| "trust_remote_code": true | |
| }, | |
| "model_type": "neobert", | |
| "pretrained_model_name_or_path": "google-bert/bert-base-uncased", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.2", | |
| "trust_remote_code": true | |
| }, | |
| "model_type": "neobert", | |
| "n_head_layers": 2, | |
| "pretrained_model_name_or_path": "google-bert/bert-base-uncased", | |
| "transformers_version": "4.56.0", | |
| "trust_remote_code": true | |
| }, | |
| "model_type": "neobert", | |
| "n_head_layers": 2, | |
| "pretrained_model_name_or_path": "google-bert/bert-base-uncased", | |
| "transformers_version": "4.56.2", | |
| "trust_remote_code": true | |
| }, | |
| "max_length": 4096, | |
| "model_type": "neobert", | |
| "n_head_layers": 2, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 28, | |
| "pad_token_id": 0, | |
| "pretrained_model_name_or_path": "google-bert/bert-base-uncased", | |
| "transformers_version": "4.56.2", | |
| "trust_remote_code": true, | |
| "vocab_size": 30522 | |
| } | |