This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. It maps sentences & paragraphs to a 1024-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: Snowflake/snowflake-arctic-embed-l
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 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}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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})
  (2): Normalize()
)

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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("vivnatan/legal-ft-20c85cc6-30d1-49ca-97e6-cce1045a4b4a")
# Run inference
sentences = [
    'How does the author describe the clarity of the term "agents"?',
    '“Agents” still haven’t really happened yet\nI find the term “agents” extremely frustrating. It lacks a single, clear and widely understood meaning... but the people who use the term never seem to acknowledge that.\nIf you tell me that you are building “agents”, you’ve conveyed almost no information to me at all. Without reading your mind I have no way of telling which of the dozens of possible definitions you are talking about.',
    'OpenAI made GPT-4o free for all users in May, and Claude 3.5 Sonnet was freely available from its launch in June. This was a momentus change, because for the previous year free users had mostly been restricted to GPT-3.5 level models, meaning new users got a very inaccurate mental model of what a capable LLM could actually do.\nThat era appears to have ended, likely permanently, with OpenAI’s launch of ChatGPT Pro. This $200/month subscription service is the only way to access their most capable model, o1 Pro.\nSince the trick behind the o1 series (and the future models it will undoubtedly inspire) is to expend more compute time to get better results, I don’t think those days of free access to the best available models are likely to return.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Evaluation

Metrics

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8417
cosine_accuracy@3	0.975
cosine_accuracy@5	0.9917
cosine_accuracy@10	1.0
cosine_precision@1	0.8417
cosine_precision@3	0.325
cosine_precision@5	0.1983
cosine_precision@10	0.1
cosine_recall@1	0.8417
cosine_recall@3	0.975
cosine_recall@5	0.9917
cosine_recall@10	1.0
cosine_ndcg@10	0.9332
cosine_mrr@10	0.9106
cosine_map@100	0.9106

Training Details

Training Dataset

Unnamed Dataset

Size: 780 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 780 samples:
sentence_0 sentence_1
type string string
details
min: 10 tokens
mean: 17.51 tokens
max: 34 tokens
min: 43 tokens
mean: 135.32 tokens
max: 214 tokens

Samples:

sentence_0	sentence_1
`What is the main discovery about Large Language Models (LLMs) in the past 24-36 months?`	Here’s the sequel to this post: Things we learned about LLMs in 2024.[object Object]Large Language Models[object Object]In the past 24-36 months, our species has discovered that you can take a GIANT corpus of text, run it through a pile of GPUs, and use it to create a fascinating new kind of software.[object Object]LLMs can do a lot of things. They can answer questions, summarize documents, translate from one language to another, extract information and even write surprisingly competent code.[object Object]They can also help you cheat at your homework, generate unlimited streams of fake content and be used for all manner of nefarious purposes.
`What resources are used to create Large Language Models?`	Here’s the sequel to this post: Things we learned about LLMs in 2024.[object Object]Large Language Models[object Object]In the past 24-36 months, our species has discovered that you can take a GIANT corpus of text, run it through a pile of GPUs, and use it to create a fascinating new kind of software.[object Object]LLMs can do a lot of things. They can answer questions, summarize documents, translate from one language to another, extract information and even write surprisingly competent code.[object Object]They can also help you cheat at your homework, generate unlimited streams of fake content and be used for all manner of nefarious purposes.
`What are some of the capabilities of LLMs mentioned in the context?`	Here’s the sequel to this post: Things we learned about LLMs in 2024.[object Object]Large Language Models[object Object]In the past 24-36 months, our species has discovered that you can take a GIANT corpus of text, run it through a pile of GPUs, and use it to create a fascinating new kind of software.[object Object]LLMs can do a lot of things. They can answer questions, summarize documents, translate from one language to another, extract information and even write surprisingly competent code.[object Object]They can also help you cheat at your homework, generate unlimited streams of fake content and be used for all manner of nefarious purposes.

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 10
per_device_eval_batch_size: 10
num_train_epochs: 10
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: 10
per_device_eval_batch_size: 10
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: 10
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: False
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}
tp_size: 0
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
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

Epoch	Step	Training Loss	cosine_ndcg@10
0.6410	50	-	0.9199
1.0	78	-	0.9322
1.2821	100	-	0.9351
1.9231	150	-	0.9415
2.0	156	-	0.9434
2.5641	200	-	0.9438
3.0	234	-	0.9404
3.2051	250	-	0.9432
3.8462	300	-	0.9345
4.0	312	-	0.9356
4.4872	350	-	0.9393
5.0	390	-	0.9358
5.1282	400	-	0.9316
5.7692	450	-	0.9335
6.0	468	-	0.9350
6.4103	500	1.3465	0.9412
7.0	546	-	0.9375
7.0513	550	-	0.9406
7.6923	600	-	0.9410
8.0	624	-	0.9375
8.3333	650	-	0.9333
8.9744	700	-	0.9375
9.0	702	-	0.9375
9.6154	750	-	0.9332
10.0	780	-	0.9332

Framework Versions

Python: 3.11.12
Sentence Transformers: 4.1.0
Transformers: 4.51.3
PyTorch: 2.6.0+cu124
Accelerate: 1.6.0
Datasets: 3.5.1
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

MatryoshkaLoss

bibtex

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

bibtex

@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}
}

	sentence_0	sentence_1
type	string	string
details	min: 10 tokens mean: 17.51 tokens max: 34 tokens	min: 43 tokens mean: 135.32 tokens max: 214 tokens