--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:21769 - loss:MultipleNegativesRankingLoss base_model: HIT-TMG/KaLM-embedding-multilingual-mini-v1 widget: - source_sentence: 'Blooming Canals of Venice, Italy. by: [IG] ' sentences: - This comparison shows the values of gasoline in Cádiz and in Gibraltar in 2021 The comparison of fuel prices circulates in Spain at least since 2018 - Genuine image of a Venice canal laden with lotus blossoms The lotus blossoms were digitally inserted into this image by a graphic artist - PT deputy presented PL for police to carry unloaded weapons Bill "5439/2022" for police officers to carry unloaded weapons does not exist - source_sentence: 'The story of a young mother in Italy who is dying due to corona, makes a last request to stop her 18-month-old baby''s incessant crying. The doctor allowed by covering his whole body with transparent wax and then placing the baby on his chest, miraculously the baby remained silent and his mother also remained silent forever. Apparently, a mother''s love for a child has no limits and has a very strange aura as Allah swt said and the Messenger of Allah reminded. Make it a lesson about mother''s love.. Greetings to all mothers especially my mother.. Puan Hjh Ashakiah Basri...... ' sentences: - Photo shows a COVID-19 victim in Italy holding her child for the last time This photo shows a baby waiting for a bone marrow transplant in the United States in 1985 - Applesauce tests positive for covid-19 antigens The video of the positive antigen test on applesauce does not show that these tests are useless - '"Submission to Rouen" with the removal of the statue of Napoleon 1st No, the removal of the statue of Napoleon I in Rouen is unrelated to the controversies linked to colonial history' - source_sentence: 'COVID-19 - HUNT FOR AFRICANS IN CHINA This is the real hell that the whole black community in China is going through in its last days. Accused by a frank Chinese population of being carriers of the COVID-19 virus, although the African continent was one of the last to experience this virus and especially the least affected at present, black Africans, are victims of another severe and cruel form of discrimination in China. They are brutally chased from their homes, banned and rejected in all hotels, violently beaten in the streets. A real open sky in this country where the population is spread all over Africa and occupies a place of choice in our African society. The Kenyan government has therefore given an Ultimatum to the entire Chinese community residing in the country, so that it go away in a short time.. AFRICAN PEOPLE, UNITY IN OUR CONTINENT SHOULD BE AN EMERGENCY MISSION . ' sentences: - Video of flooded metro as Typhoon In-Fa hit Shanghai The video predates Typhoon In-Fa that hit eastern China in 2021 - Video shows attack on Africans in China No, this video does not show an attack on Africans in China but a fight in New York a month ago - These figures show that Covid-19 kills fewer people than many other diseases/accidents Figures that put the mortality due to Covid-19 in the world into perspective? Beware of these comparisons - source_sentence: 'I will not be vaccinated. - Swiss Vaccine Protection Federation How to protect us / - see below i vaccinate will not receive Dr. Gisele Werner: Prevention, like many colleagues waiting before getting vaccinated It is recommended. We believe in this novel gene therapy necessary to ensure safety There is no possibility. This vaccine against COVID 19 is prevent the spread of the virus and barrier gestures does not release We have long-term side effects I don''t know until now more than benefits witness the danger there is. Look out! Swiss Vaccine Protection Federation This information campaign aims to address the risks inherent in vaccination. Supported by knowledgeable Swiss citizens and doctors. Sante' sentences: - This picture shows a man in hospital after eating a bat after a novel coronavirus outbreak This picture has circulated on a fundraising site for men with lung pain unrelated to the novel coronavirus - Cardiologist McCullough affirms “without the slightest shadow of a doubt” that “the Covid-19 vaccine causes myocarditis”, “and the FDA knows that because there are 200 published scientific documents that prove it Dr. Peter McCullough's sayings about vaccines against covid-19 verified - Swiss medical orgnisation publishes this poster to advise people not to get vaccinated against Covid-19. This poster has been doctored from a health notice promoting the coronavirus jab - source_sentence: 'The putschists sold out Mali Read it is extremely serious MOVEMENT COORDINATION OF AZAWAD (CMA) - having regard to the CMA charter - having regard to the Internal Regulations of the Management Committee - given the need for the service STEERING COMMITTEE Decision N°013/Pdt CMA Bearing the Boundary of the State of AZAWAD and the State of Mali. The President of the CMA: تنسيقية الحركات الأزوادية DECIDED: Article 1: The start of bormage works between the State of Azawad and the State of Mali in order to avoid all conflicts of interest. Article 2: Prohibition of all military operations without the prior agreement of 40-1tl.: 0:51 +1.XIA the State of Azawad and its partners (Barkhane and Minusma) who provided efforts for our independence. Amplification: EMGA/CMA.. Fama area of Gao01 Minusma Kidal: Barkhane Kidal: Article 3: This decision takes effect from the date of its signature and will be recorded and published wherever needed. 01 ...01 01 Kidal, February 2, 2004 THE PRESIDENTIA SIDI IBRAHIM OULD SIDATT' sentences: - 'Pfizer announces Covid-19 vaccine update with Microsoft chip for symptom reduction Pfizer did not announce an agreement with Microsoft: the article about the chip in the covid vaccine is a satire' - Selensyj indicated rabbit ears to Putin here. This image of Zelenskyy showing Putin rabbit ears is manipulated - The CMA announces the start of the demarcation between the State of Azawad and the State of Mali Please note, this document attributed to former Tuareg separatist rebels is a fake pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on HIT-TMG/KaLM-embedding-multilingual-mini-v1 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [HIT-TMG/KaLM-embedding-multilingual-mini-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-v1). It maps sentences & paragraphs to a 896-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:** [HIT-TMG/KaLM-embedding-multilingual-mini-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-v1) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 896 dimensions - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: Qwen2Model (1): Pooling({'word_embedding_dimension': 896, '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: ```bash 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 sentences = [ 'The putschists sold out Mali Read it is extremely serious MOVEMENT COORDINATION OF AZAWAD (CMA) - having regard to the CMA charter - having regard to the Internal Regulations of the Management Committee - given the need for the service STEERING COMMITTEE Decision N°013/Pdt CMA Bearing the Boundary of the State of AZAWAD and the State of Mali. The President of the CMA: تنسيقية الحركات الأزوادية DECIDED: Article 1: The start of bormage works between the State of Azawad and the State of Mali in order to avoid all conflicts of interest. Article 2: Prohibition of all military operations without the prior agreement of 40-1tl.: 0:51 +1.XIA the State of Azawad and its partners (Barkhane and Minusma) who provided efforts for our independence. Amplification: EMGA/CMA.. Fama area of Gao01 Minusma Kidal: Barkhane Kidal: Article 3: This decision takes effect from the date of its signature and will be recorded and published wherever needed. 01 ...01 01 Kidal, February 2, 2004 THE PRESIDENTIA SIDI IBRAHIM OULD SIDATT', 'The CMA announces the start of the demarcation between the State of Azawad and the State of Mali Please note, this document attributed to former Tuareg separatist rebels is a fake', 'Pfizer announces Covid-19 vaccine update with Microsoft chip for symptom reduction Pfizer did not announce an agreement with Microsoft: the article about the chip in the covid vaccine is a satire', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 896] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 21,769 training samples * Columns: sentence_0 and sentence_1 * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | sentence_0 | sentence_1 | |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | CAMP CANBERRA - the biggest gathering in Canberra of all time! Police report they let 1.4 million vehicles through and that was yesterday. People were still pouring in overnight and all morning. Most vehicles had more than one person in them. Amongst the vehicles there were 100s of special buses that came full of people from all over Australia. So doubling that number can still be considered quite a conservative estimate. Population of Australia : 25 million. When 5 million show up, that's 20% of the country and there's HEAPS of us that couldn't make it! Here's a HUGE SHOUT-OUT and THANK YOU to ALL who did! Lighting a candle for all who are rising up all over the world. I Love it when we stand Peacefully in Love as One! TO THE REBELS This is for ones that see the through the deception and lies. That actively resist tyranny and live a life which is lead by their own intuition and heart. They are owned by no one. To the brave Women and Men who courageously risk their reputation and relat... | Anti-vaccine mandate protests attract over one million vehicles to Canberra Facebook posts share false claim about size of anti-vaccine mandate protest in Australia | | Typhoon fireworks land in Shanghai emergency (12) The extension line of Shanghai Metro No. 1 began to flood. video | Video of flooded metro as Typhoon In-Fa hit Shanghai The video predates Typhoon In-Fa that hit eastern China in 2021 | | WHO declares PCR tests unreliable At the same time as Joe Biden was sworn in as the new US President, the WHO questioned the reliability of the PCR test. I can't remember who kept mentioning this before? Was that me in the end? According to the WHO, a PCR test alone is not enough to detect an infection. How many millions of people have sat in quarantine for nothing? Positive test results in symptom-free people are not usable! For my critical statements about the PCR test, I was disparaged by self-appointed fact-checkers. I also remember a discussion on Servus-TV, where Prof. Manfred Spitzer, whom I valued before, suppressed any criticism of the PCR test in a highly authoritarian and almost aggressive manner. "Positive PCR test means infected!" We now know that the basis for the tightened and probably ever-extended lockdown is a political and not a scientific decision. Of course, politicians refer to scientists. However, only to those who support the political course. Two brave editors ... | The WHO confirmed that PCR tests are unsuitable for detecting corona WHO recommendations on PCR tests are misinterpreted | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 2 - `per_device_eval_batch_size`: 2 - `num_train_epochs`: 1 - `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`: 2 - `per_device_eval_batch_size`: 2 - `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`: 1 - `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} - `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 | Epoch | Step | Training Loss | |:------:|:-----:|:-------------:| | 0.0459 | 500 | 0.0142 | | 0.0919 | 1000 | 0.0367 | | 0.1378 | 1500 | 0.0444 | | 0.1837 | 2000 | 0.0581 | | 0.2297 | 2500 | 0.045 | | 0.2756 | 3000 | 0.0736 | | 0.3215 | 3500 | 0.0567 | | 0.3675 | 4000 | 0.0314 | | 0.4134 | 4500 | 0.0362 | | 0.4593 | 5000 | 0.029 | | 0.5053 | 5500 | 0.0621 | | 0.5512 | 6000 | 0.0328 | | 0.5972 | 6500 | 0.0279 | | 0.6431 | 7000 | 0.0343 | | 0.6890 | 7500 | 0.0251 | | 0.7350 | 8000 | 0.0437 | | 0.7809 | 8500 | 0.0328 | | 0.8268 | 9000 | 0.0123 | | 0.8728 | 9500 | 0.0177 | | 0.9187 | 10000 | 0.0332 | | 0.9646 | 10500 | 0.0214 | ### Framework Versions - Python: 3.11.11 - Sentence Transformers: 3.4.1 - Transformers: 4.48.3 - PyTorch: 2.5.1+cu124 - Accelerate: 1.3.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## 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} } ```