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("Tombiczek/all-MiniLM-L6-v2_fine-tuned-cosqa")
# Run inference
sentences = [
    'python qpushbutton resize in grid layout',
    'def resize(self, width, height):\n        """\n        Pyqt specific resize callback.\n        """\n        if not self.fbo:\n            return\n\n        # pyqt reports sizes in actual buffer size\n        self.width = width // self.widget.devicePixelRatio()\n        self.height = height // self.widget.devicePixelRatio()\n        self.buffer_width = width\n        self.buffer_height = height\n\n        super().resize(width, height)',
    'def __delitem__(self, resource):\n        """Remove resource instance from internal cache"""\n        self.__caches[type(resource)].pop(resource.get_cache_internal_key(), None)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.5830, 0.0179],
#         [0.5830, 1.0000, 0.1409],
#         [0.0179, 0.1409, 1.0000]])

Evaluation

Metrics

Information Retrieval

Dataset: cosqa-valid
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.802
cosine_accuracy@3	0.964
cosine_accuracy@5	0.992
cosine_accuracy@10	0.998
cosine_precision@10	0.0998
cosine_recall@10	0.998
cosine_ndcg@10	0.9137
cosine_mrr@10	0.8851
cosine_map@100	0.8852

Training Details

Training Dataset

Unnamed Dataset

Size: 9,008 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: 6 tokens
mean: 9.61 tokens
max: 23 tokens
min: 38 tokens
mean: 87.19 tokens
max: 256 tokens

Samples:

sentence_0	sentence_1
`python save ndarray to json`	def deserialize_ndarray_npy(d):[object Object] """[object Object] Deserializes a JSONified :obj:[object Object] that was created using numpy's[object Object] :obj:[object Object] function.[object Object][object Object] Args:[object Object] d (:obj:[object Object]): A dictionary representation of an :obj:[object Object] object, created[object Object] using :obj:[object Object].[object Object][object Object] Returns:[object Object] An :obj:[object Object] object.[object Object] """[object Object] with io.BytesIO() as f:[object Object] f.write(json.loads(d['npy']).encode('latin-1'))[object Object] f.seek(0)[object Object] return np.load(f)
`python delay between loop`	`def seconds(num):[object Object] """[object Object] Pause for this many seconds[object Object] """[object Object] now = pytime.time()[object Object] end = now + num[object Object] until(end)`
`python how to read a text file to dict`	`def read_dict_from_file(file_path):[object Object] """[object Object] Read a dictionary of strings from a file[object Object] """[object Object] with open(file_path) as file:[object Object] lines = file.read().splitlines()[object Object][object Object] obj = {}[object Object] for line in lines:[object Object] key, value = line.split(':', maxsplit=1)[object Object] obj[key] = eval(value)[object Object][object Object] return obj`

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: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 10
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: 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: 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
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	cosqa-valid_cosine_ndcg@10
0.8881	500	0.0925	-
1.0	563	-	0.8889
1.7762	1000	0.0536	-
2.0	1126	-	0.8955
2.6643	1500	0.0419	-
3.0	1689	-	0.8999
3.5524	2000	0.0365	-
4.0	2252	-	0.9087
4.4405	2500	0.0308	-
5.0	2815	-	0.9060
5.3286	3000	0.0283	-
6.0	3378	-	0.9085
6.2167	3500	0.0263	-
7.0	3941	-	0.9116
7.1048	4000	0.0227	-
7.9929	4500	0.0234	-
8.0	4504	-	0.9119
8.8810	5000	0.0214	-
9.0	5067	-	0.9066
9.7691	5500	0.0216	-
10.0	5630	-	0.9137

Framework Versions

Python: 3.10.18
Sentence Transformers: 5.1.2
Transformers: 4.57.1
PyTorch: 2.9.0
Accelerate: 1.11.0
Datasets: 4.3.0
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}
}

	sentence_0	sentence_1
type	string	string
details	min: 6 tokens mean: 9.61 tokens max: 23 tokens	min: 38 tokens mean: 87.19 tokens max: 256 tokens