This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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})
  (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("sentence_transformers_model_id")
# Run inference
queries = [
    "check if address is valid python",
]
documents = [
    'def is_valid_ipv6(ip_str):\n    """\n    Check the validity of an IPv6 address\n    """\n    try:\n        socket.inet_pton(socket.AF_INET6, ip_str)\n    except socket.error:\n        return False\n    return True',
    'def longest_run_1d(arr):\n    """Return the length of the longest consecutive run of identical values.\n\n    Parameters\n    ----------\n    arr : bool array\n      Input array\n\n    Returns\n    -------\n    int\n      Length of longest run.\n    """\n    v, rl = rle_1d(arr)[:2]\n    return np.where(v, rl, 0).max()',
    'def dict_to_enum_fn(d: Dict[str, Any], enum_class: Type[Enum]) -> Enum:\n    """\n    Converts an ``dict`` to a ``Enum``.\n    """\n    return enum_class[d[\'name\']]',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.6137, -0.0250, -0.1585]])

Training Details

Training Dataset

Unnamed Dataset

Size: 9,020 training samples
Columns: query, document, and score
Approximate statistics based on the first 1000 samples:
query document score
type string string int
details
min: 6 tokens
mean: 9.67 tokens
max: 21 tokens
min: 40 tokens
mean: 86.17 tokens
max: 256 tokens
1: 100.00%

Samples:

query	document	score
`1d array in char datatype in python`	`def _convert_to_array(array_like, dtype):[object Object] """[object Object] Convert Matrix attributes which are array-like or buffer to array.[object Object] """[object Object] if isinstance(array_like, bytes):[object Object] return np.frombuffer(array_like, dtype=dtype)[object Object] return np.asarray(array_like, dtype=dtype)`	`1`
`python condition non none`	def _not(condition=None, kwargs):[object Object] """[object Object] Return the opposite of input condition.[object Object][object Object] :param condition: condition to process.[object Object][object Object] :result: not condition.[object Object] :rtype: bool[object Object] """[object Object][object Object] result = True[object Object][object Object] if condition is not None:[object Object] result = not run(condition, kwargs)[object Object][object Object] return result	`1`
`accessing a column from a matrix in python`	def get_column(self, X, column):[object Object] """Return a column of the given matrix.[object Object][object Object] Args:[object Object] X: [object Object] or [object Object].[object Object] column: [object Object] or [object Object].[object Object][object Object] Returns:[object Object] np.ndarray: Selected column.[object Object] """[object Object] if isinstance(X, pd.DataFrame):[object Object] return X[column].values[object Object][object Object] return X[:, column]	`1`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim", 4 "gather_across_devices": false 5}

Evaluation Dataset

Unnamed Dataset

Size: 500 evaluation samples
Columns: query, document, and score
Approximate statistics based on the first 500 samples:
query document score
type string string int
details
min: 6 tokens
mean: 9.71 tokens
max: 21 tokens
min: 42 tokens
mean: 87.19 tokens
max: 256 tokens
1: 100.00%

Samples:

query	document	score
`python check if a variable is iterable`	`def is_iterable_but_not_string(obj):[object Object] """[object Object] Determine whether or not obj is iterable but not a string (eg, a list, set, tuple etc).[object Object] """[object Object] return hasattr(obj, '[object Object]') and not isinstance(obj, str) and not isinstance(obj, bytes)`	`1`
`how to prevent a file from modifying python`	`def make_file_readable (filename):[object Object] """Make file user readable if it is not a link."""[object Object] if not os.path.islink(filename):[object Object] util.set_mode(filename, stat.S_IRUSR)`	`1`
`how to make functions that returns a function python`	`def apply(filter):[object Object] """Manufacture decorator that filters return value with given function.[object Object][object Object] [object Object]:[object Object] Callable that takes a single parameter.[object Object] """[object Object] def decorator(callable):[object Object] return lambda args, kwargs: filter(callable(args, **kwargs))[object Object] return decorator`	`1`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim", 4 "gather_across_devices": false 5}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 7
warmup_ratio: 0.1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
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: 1.0
num_train_epochs: 7
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
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}
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
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: False
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: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss
0.7092	100	0.2775	-
1.0	141	-	0.1604
1.4184	200	0.1842	-
2.0	282	-	0.1411
2.1277	300	0.1482	-
2.8369	400	0.1164	-
3.0	423	-	0.1278
3.5461	500	0.1073	-
4.0	564	-	0.1177
4.2553	600	0.0936	-
4.9645	700	0.0831	-
5.0	705	-	0.1114
5.6738	800	0.0748	-
6.0	846	-	0.1078
6.3830	900	0.0746	-

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.1.1
Transformers: 4.56.2
PyTorch: 2.8.0+cu128
Accelerate: 1.10.1
Datasets: 4.1.1
Tokenizers: 0.22.1

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",
}

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}
}

	query	document	score
type	string	string	int
details	min: 6 tokens mean: 9.67 tokens max: 21 tokens	min: 40 tokens mean: 86.17 tokens max: 256 tokens	1: 100.00%

DornierDo17/all-MiniLM-L6-v2-CosQA

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Training Details

Training Dataset

Unnamed Dataset

Evaluation Dataset

Unnamed Dataset

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Logs

Framework Versions

Citation

BibTeX

Sentence Transformers

MultipleNegativesRankingLoss

DornierDo17/
all-MiniLM-L6-v2-CosQA