Instructions to use Tskunz/pg-simcse-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tskunz/pg-simcse-bert with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Tskunz/pg-simcse-bert")

sentences = [
"t started. [5]It can be dangerous to delay turning yourself into a company, because one or more of the founders might decide to split off and start another company doing the same thing. This does happen. So when you set up the company, as well as as apportioning the stock, you should get all the founders to sign something agreeing that everyone's ideas belong to this company, and that this company is going to be everyone's only job.[If this were a movie, ominous music would begin here.]While you're at it, you should ask what else they've signed. One of the worst things that can happen to a startup is to run into intellectual property problems. We did, and it came closer to killing us than any competitor ever did. As we were in the middle of getting bought, we discovered that one of our people had, early on, been bound by an agreement that said all his ideas belonged to the giant company that was paying for him to go to grad school. In theory, that could have meant someone else owned big chunks of our software. So the acquisition came to a screeching halt while we tried to sort this out. The problem was, since we'd been about to be acquired, we'd allowed ourselves to run low on cash",
"what we should expect in the future is more of the same. Indeed, we should expect both the number and wealth of founders to grow, because every decade it gets easier to start a startup. Part of the reason it's getting easier to start a startup is social. Society is (re)assimilating the concept. If you start one now, your parents won't freak out the way they would have a generation ago, and knowledge about how to do it is much more widespread. But the main reason it's easier to start a startup now is that it's cheaper. Technology has driven down the cost of both building products and acquiring customers. The decreasing cost of starting a startup has in turn changed the balance of power between founders and investors. Back when starting a startup meant building a factory, you needed investors' permission to do it at all. But now investors need founders more than founders need investors, and that, combined with the increasing amount of venture capital available, has driven up valuations. [8]So the decreasing cost of starting a startup increases the number of rich people in two ways: it means that more people start them, and that those who do can raise money on better terms. But there'",
"e a company when, as sometimes happens, its whole market dies, just as property managers can't save you from the building burning down. But a company that managed a large enough number of companies could say to all its clients: we'll combine the revenues from all your companies, and pay you your proportionate share. If such management companies existed, they'd offer the maximum of freedom and security. Someone would run your company for you, and you'd be protected even if it happened to die. Let's think about how such a management company might be organized. The simplest way would be to have a new kind of stock representing the total pool of companies they were managing. When you signed up, you'd trade your company's stock for shares of this pool, in proportion to an estimate of your company's value that you'd both agreed upon. Then you'd automatically get your share of the returns of the whole pool. The catch is that because this kind of trade would be hard to undo, you couldn't switch management companies. But there's a way they could fix that: suppose all the company management companies got together and agreed to allow their clients to exchange shares in all their pools. Then y",
"t started. [5]It can be dangerous to delay turning yourself into a company, because one or more of the founders might decide to split off and start another company doing the same thing. This does happen. So when you set up the company, as well as as apportioning the stock, you should get all the founders to sign something agreeing that everyone's ideas belong to this company, and that this company is going to be everyone's only job.[If this were a movie, ominous music would begin here.]While you're at it, you should ask what else they've signed. One of the worst things that can happen to a startup is to run into intellectual property problems. We did, and it came closer to killing us than any competitor ever did. As we were in the middle of getting bought, we discovered that one of our people had, early on, been bound by an agreement that said all his ideas belonged to the giant company that was paying for him to go to grad school. In theory, that could have meant someone else owned big chunks of our software. So the acquisition came to a screeching halt while we tried to sort this out. The problem was, since we'd been about to be acquired, we'd allowed ourselves to run low on cash"
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle

SentenceTransformer

This is a sentence-transformers model trained. 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
Maximum Sequence Length: 512 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': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    "ded to take occasional vacations. [5]The only way to find the limit is by crossing it. Cultivate a sensitivity to the quality of the work you're doing, and then you'll notice if it decreases because you're working too hard. Honesty is critical here, in both directions: you have to notice when you're being lazy, but also when you're working too hard. And if you think there's something admirable about working too hard, get that idea out of your head. You're not merely getting worse results, but getting them because you're showing off — if not to other people, then to yourself. [6]Finding the limit of working hard is a constant, ongoing process, not something you do just once. Both the difficulty of the work and your ability to do it can vary hour to hour, so you need to be constantly judging both how hard you're trying and how well you're doing. Trying hard doesn't mean constantly pushing yourself to work, though. There may be some people who do, but I think my experience is fairly typical, and I only have to push myself occasionally when I'm starting a project or when I encounter some sort of check. That's when I'm in danger of procrastinating. But once I get rolling, I tend to keep",
    "ded to take occasional vacations. [5]The only way to find the limit is by crossing it. Cultivate a sensitivity to the quality of the work you're doing, and then you'll notice if it decreases because you're working too hard. Honesty is critical here, in both directions: you have to notice when you're being lazy, but also when you're working too hard. And if you think there's something admirable about working too hard, get that idea out of your head. You're not merely getting worse results, but getting them because you're showing off — if not to other people, then to yourself. [6]Finding the limit of working hard is a constant, ongoing process, not something you do just once. Both the difficulty of the work and your ability to do it can vary hour to hour, so you need to be constantly judging both how hard you're trying and how well you're doing. Trying hard doesn't mean constantly pushing yourself to work, though. There may be some people who do, but I think my experience is fairly typical, and I only have to push myself occasionally when I'm starting a project or when I encounter some sort of check. That's when I'm in danger of procrastinating. But once I get rolling, I tend to keep",
    ' is not in itself bad, only when it\'s camouflage on insipid form.) Similarly, in painting, a still life of a few carefully observed and solidly modelled objects will tend to be more interesting than a stretch of flashy but mindlessly repetitive painting of, say, a lace collar. In writing it means: say what you mean and say it briefly. It seems strange to have to emphasize simplicity. You\'d think simple would be the default. Ornate is more work. But something seems to come over people when they try to be creative. Beginning writers adopt a pompous tone that doesn\'t sound anything like the way they speak. Designers trying to be artistic resort to swooshes and curlicues. Painters discover that they\'re expressionists. It\'s all evasion. Underneath the long words or the "expressive" brush strokes, there is not much going on, and that\'s frightening. When you\'re forced to be simple, you\'re forced to face the real problem. When you can\'t deliver ornament, you have to deliver substance. Good design is timeless. In math, every proof is timeless unless it contains a mistake. So what does Hardy mean when he says there is no permanent place for ugly mathematics? He means the same thing Kelly Joh',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  1.0000, -0.1102],
#         [ 1.0000,  1.0000, -0.1102],
#         [-0.1102, -0.1102,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 1,668 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 26 tokens
mean: 257.69 tokens
max: 345 tokens

min: 26 tokens
mean: 257.69 tokens
max: 345 tokens

	sentence_0	sentence_1
type	string	string
details	min: 26 tokens mean: 257.69 tokens max: 345 tokens	min: 26 tokens mean: 257.69 tokens max: 345 tokens

Samples:

sentence_0	sentence_1
ts raison d'etre—is that it offers something otherwise impossible to obtain: a way of measuring that. In many businesses, it just makes more sense for companies to get technology by buying startups rather than developing it in house. You pay more, but there is less risk, and risk is what big companies don't want. It makes the guys developing the technology more accountable, because they only get paid if they build the winner. And you end up with better technology, created faster, because things are made in the innovative atmosphere of startups instead of the bureaucratic atmosphere of big companies. Our startup, Viaweb, was built to be sold. We were open with investors about that from the start. And we were careful to create something that could slot easily into a larger company. That is the pattern for the future.9. CaliforniaThe Bubble was a California phenomenon. When I showed up in Silicon Valley in 1998, I felt like an immigrant from Eastern Europe arriving in America in 1900. Eve...	ts raison d'etre—is that it offers something otherwise impossible to obtain: a way of measuring that. In many businesses, it just makes more sense for companies to get technology by buying startups rather than developing it in house. You pay more, but there is less risk, and risk is what big companies don't want. It makes the guys developing the technology more accountable, because they only get paid if they build the winner. And you end up with better technology, created faster, because things are made in the innovative atmosphere of startups instead of the bureaucratic atmosphere of big companies. Our startup, Viaweb, was built to be sold. We were open with investors about that from the start. And we were careful to create something that could slot easily into a larger company. That is the pattern for the future.9. CaliforniaThe Bubble was a California phenomenon. When I showed up in Silicon Valley in 1998, I felt like an immigrant from Eastern Europe arriving in America in 1900. Eve...
image rendered with more pixels. One consequence is that some old recipes may have become obsolete. At the very least we have to go back and figure out if they were really recipes for wisdom or intelligence. But the really striking change, as intelligence and wisdom drift apart, is that we may have to decide which we prefer. We may not be able to optimize for both simultaneously. Society seems to have voted for intelligence. We no longer admire the sage—not the way people did two thousand years ago. Now we admire the genius. Because in fact the distinction we began with has a rather brutal converse: just as you can be smart without being very wise, you can be wise without being very smart. That doesn't sound especially admirable. That gets you James Bond, who knows what to do in a lot of situations, but has to rely on Q for the ones involving math. Intelligence and wisdom are obviously not mutually exclusive. In fact, a high average may help support high peaks. But there are reasons t...	image rendered with more pixels. One consequence is that some old recipes may have become obsolete. At the very least we have to go back and figure out if they were really recipes for wisdom or intelligence. But the really striking change, as intelligence and wisdom drift apart, is that we may have to decide which we prefer. We may not be able to optimize for both simultaneously. Society seems to have voted for intelligence. We no longer admire the sage—not the way people did two thousand years ago. Now we admire the genius. Because in fact the distinction we began with has a rather brutal converse: just as you can be smart without being very wise, you can be wise without being very smart. That doesn't sound especially admirable. That gets you James Bond, who knows what to do in a lot of situations, but has to rely on Q for the ones involving math. Intelligence and wisdom are obviously not mutually exclusive. In fact, a high average may help support high peaks. But there are reasons t...
he mastered a new kind of farming. I've seen the lever of technology grow visibly in my own time. In high school I made money by mowing lawns and scooping ice cream at Baskin-Robbins. This was the only kind of work available at the time. Now high school kids could write software or design web sites. But only some of them will; the rest will still be scooping ice cream. I remember very vividly when in 1985 improved technology made it possible for me to buy a computer of my own. Within months I was using it to make money as a freelance programmer. A few years before, I couldn't have done this. A few years before, there was no such thing as a freelance programmer. But Apple created wealth, in the form of powerful, inexpensive computers, and programmers immediately set to work using it to create more. As this example suggests, the rate at which technology increases our productive capacity is probably exponential, rather than linear. So we should expect to see ever-increasing variation in i...	he mastered a new kind of farming. I've seen the lever of technology grow visibly in my own time. In high school I made money by mowing lawns and scooping ice cream at Baskin-Robbins. This was the only kind of work available at the time. Now high school kids could write software or design web sites. But only some of them will; the rest will still be scooping ice cream. I remember very vividly when in 1985 improved technology made it possible for me to buy a computer of my own. Within months I was using it to make money as a freelance programmer. A few years before, I couldn't have done this. A few years before, there was no such thing as a freelance programmer. But Apple created wealth, in the form of powerful, inexpensive computers, and programmers immediately set to work using it to create more. As this example suggests, the rate at which technology increases our productive capacity is probably exponential, rather than linear. So we should expect to see ever-increasing variation in i...

Loss: main.LoggableMNRL with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: no
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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
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}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
hub_revision: None
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
include_tokens_per_second: False
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
4.7619	500	0.1358

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.1.2
Transformers: 4.57.3
PyTorch: 2.9.0+cu126
Accelerate: 1.12.0
Datasets: 4.0.0
Tokenizers: 0.22.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

LoggableMNRL

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Downloads last month: 1

Safetensors

Model size

0.1B params

Tensor type

F32

Papers for Tskunz/pg-simcse-bert

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Paper • 1908.10084 • Published Aug 27, 2019 • 13

Efficient Natural Language Response Suggestion for Smart Reply

Paper • 1705.00652 • Published May 1, 2017