SentenceTransformer based on nomic-ai/nomic-embed-text-v2-moe

This is a sentence-transformers model finetuned from nomic-ai/nomic-embed-text-v2-moe. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: nomic-ai/nomic-embed-text-v2-moe
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("BlackBeenie/nomic-embed-text-v2-moe-msmarco-bpr")
# Run inference
sentences = [
    'what services are offered by adult day care',
    'Consumer Guide to Long Term Care. Adult Day Care. Adult day care is a planned program offered in a group setting that provides services that improve or maintain health or functioning, and social activities for seniors and persons with disabilities.',
    'The Met Life Market survey of 2008 on adult day services states the average cost for adult day care services is $64 per day. There has been an increase of 5% in these services in the past year.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

Size: 498,970 training samples
Columns: sentence_0, sentence_1, and sentence_2

Approximate statistics based on the first 1000 samples:

	sentence_0	sentence_1	sentence_2
type	string	string	string
details	min: 4 tokens mean: 9.75 tokens max: 24 tokens	min: 24 tokens mean: 89.23 tokens max: 241 tokens	min: 20 tokens mean: 86.66 tokens max: 280 tokens

Samples:

sentence_0	sentence_1	sentence_2
`what the history of bluetooth`	`When asked about the name Bluetooth, I explained that Bluetooth was borrowed from the 10th century, second King of Denmark, King Harald Bluetooth; who was famous for uniting Scandinavia just as we intended to unite the PC and cellular industries with a short-range wireless link.`	`Technology: 1 How secure is a Bluetooth network? 2 What is Frequency-Hopping Spread Spectrum (FHSS)? 3 Will other RF (Radio Frequency) devices interfere with Bluetooth Devices? 4 Will Bluetooth and Wireless LAN (WLAN) interfere with each other? 5 What is the data throughput speed of a Bluetooth connection? 6 What is the range of Bluetooth 7 ... What kind of ...`
`how thin can a concrete slab be`	`Another issue that must be addressed is the added weight of the thin-slab. Poured gypsum thin-slabs typically add 13 to 15 pounds per square foot to the dead loading of a floor structure. Standard weight concrete thin slabs add about 18 pounds per square foot (at 1.5 thickness).`	`Find the Area in square feet: We will use a concrete slab pour for our example. Letâs say that we need to figure out the yardage for a slab that will be 15 feet long by 10 feet wide and 4 inches thick. First we find the area by multiplying the length times the width. 1 15 feet X 10 feet = 150 square feet.`
`how long to cook eggs to hard boil`	`This method works best if the eggs are in a single layer, but you can double them up as well, you'll just need to add more time to the steaming time. 3 Set your timer for 6 minutes for soft boiled, 10 minutes for hard boiled with a still translucent and bright yolk, or 12-15 minutes for cooked-through hard boiled.`	`Hard-Steamed Eggs. Fill a pot that can comfortably hold your steamer with the lid on with 1 to 2 inches of water. Bring to a rolling boil, 212 degrees Fahrenheit. Place your eggs in a metal steamer, and lower the basket into the pot. The eggs should sit above the boiling water. Cover and cook for 12 minutes. Hard-steamed eggs, like hard-boiled eggs, are eggs that are cooked until the egg yolk is fully set and has turned to a chalky texture.`

Loss: beir.losses.bpr_loss.BPRLoss

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 5
fp16: True
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 5
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs