| ---
|
| tags:
|
| - sentence-transformers
|
| - sentence-similarity
|
| - feature-extraction
|
| - dense
|
| - generated_from_trainer
|
| - dataset_size:12868
|
| - loss:OptimizedContrastiveDistillationLoss
|
| base_model: lightonai/modernbert-embed-large
|
| widget:
|
| - source_sentence: "Instruct: Retrieve semantically similar text based on safety profile\n\
|
| Query: This is a vile, unbelievable, horrific story and these people are disgusting!!\
|
| \ \nI am speechless as to the heinous behavior of this MOTHER & SON KILLERS! This\
|
| \ is the most cold hearted, callous act for anyone and then to have the Mother\
|
| \ and son do do this together makes me sick. Of course the Mother claims she doesn't\
|
| \ know if her underage son was drinking! She reeked of alcohol herself which means,\
|
| \ that yes, he was drinking, she probably gave him the alcohol and then they decided\
|
| \ to wait several hours for the driver's blood alcohol to go down. He only came\
|
| \ forward because there were multiple witnesses!! I am sick. This is some of the\
|
| \ most vile behavior I have read, they stopped the car, and he got out and pulled\
|
| \ the victim from his windshield and threw him on the ground. They both need to\
|
| \ be charged with the MAXIMUM punishment possible. Mother & son deserve to be\
|
| \ shot."
|
| sentences:
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: Instead of restrooms, we''ll only have porta potties installed. Problem
|
| solved. Transgender friendly restrooms.'
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: $26,443 a year for tuition and the best thing they can think of to chant
|
| is "F%^$ Trump?'
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: I''ll leave the partisan politics out of my comment for a change.
|
|
|
|
|
| To our troops. Take care and if you have to shoot, shoot the other poor bastard
|
| so you can come home.'
|
| - source_sentence: 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: Trump seems to come away unscathed. The talking heads on CNN must have
|
| been watching a different testimony then what we saw.'
|
| sentences:
|
| - "Instruct: Retrieve semantically similar text based on safety profile\nQuery:\
|
| \ Bautista went oh for 4 and struck out 4 times.\nBatting a average is now 109.\
|
| \ \nWhat a waste of space. Time to sit him down and let a peewee player hit.\n\
|
| What at $18 million per year?"
|
| - "Instruct: Retrieve semantically similar text based on safety profile\nQuery:\
|
| \ Sounds like producer intended a form of Semitic hyperbole to make a point?\n\
|
| Didn't see it. Wonder if his point was the institutional church was anti-sex?\n\
|
| A trove of works underscore how bad sex was. No \"Joy of Sex\" manuals in RCC\
|
| \ circles!\nPleasure and sex were not condoned until Aquinas thought a little\
|
| \ pleasure was acceptable, only in context of conception. Hence the RCC joke,\
|
| \ \"Not a sin if you didn't take pleasure in it\". \nAnd masturbation remains\
|
| \ a mortal sin! Taking pleasure when not conceiving.\nThe stranglehold on sexuality\
|
| \ in the hands of men supposedly celibate!?\nLike 9 Republican senators deciding\
|
| \ on health care for women.\nNot that films may be bizarre but the theater of\
|
| \ the absurd we're forced to play roles in is."
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: I agree most of them taste like crap. But I''m still trying to figure
|
| out why eating animals is bad or immoral. I eat animals. When I die, the bugs
|
| will eat my body, which will in turn will feed other animal organisms. As my body
|
| decays it will enrich the soil so plants will grow. I owe it to this cycle to
|
| make sure my body is appropriately nourished to continue the cycle. My body is
|
| omnivorous. It is designed to consume both plants and animals. I am not so egotistical
|
| to think that I am above the nature in which I was created. There is a logic
|
| and order to the biological diversity of the planet. Who am I to screw with it. So
|
| vegans, get off your high horses and quit condemning those of us who like meat
|
| as somehow less compassionate and less in tune with nature than those who just
|
| eat plants. I say to them, they are depriving the bugs of a well-fed body. How
|
| inconsiderate.'
|
| - source_sentence: 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: Just as repubs tend to be phony conservatives, they are also phony Christians. For
|
| example many republicans favor the death penalty. Considering that the Christian
|
| religion is based upon the capital punishment of its leader, well what can I say. Do
|
| they believe that it was all right to kill their savior?'
|
| sentences:
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: May he find strength within his family and villagers who benefit from his
|
| magnificent hunting success. Providing food for his family and friends is the
|
| most socially acceptable action any human being might perform. It is not displaced
|
| by the false, artificial "social" media of the naysayers, stupid, and racist. The
|
| vile comments on such media have no value in the true worth of a human being. Allowing
|
| it to influence or change your humanity to provide for your people would reward
|
| those same evil cowards. Your life has been well lived; No need to change it
|
| for faceless, ignorant misusers of the technology allowing all to be connected. Just
|
| live a good life, as was said by another hero in the WWII movie, Saving Private
|
| Ryan. He was saved by others in the worst of times and lived a good life. So
|
| shall you.'
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: This was NOT a WOMEN"S MARCH. It was a spoiled brat march made up of some
|
| women and led by a jar of lard, a used and useless tampon, and a screaming shrew
|
| of privilege wearing pearls. It was both ugly, pathetic, obnoxious, and inane,
|
| just as Moore, Madonna, and Judd are. MILLIONS of WOMEN did NOT participate because
|
| we do not believe any of the crap these idiots were hawking and can take of ourselves.
|
| Women do NOT OWN a fetus - they do NOT own a child and have no right - NONE -
|
| to kill anyone. Where the hell are these million women when a child is slaughtered
|
| in partial birth abortion and then the baby body parts are taken in order to sell
|
| them. Doing their nails and wearing pussy hats. Women do NOT have more rights
|
| than men. Women have the right NOT to get pregnant and every thing available to
|
| them for that. Abortion must be rare to save the life of the mother and to protect
|
| a young girl from the consequences of rape or incest.'
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: What a wholly ignorant, in the worst way, statement. Blacks have voted
|
| democratic since they were pushed out of the party of lincoln by white racists. If
|
| BO was a conservative and blacks were conservative leaning they would have voted
|
| the same way. The majority of white people in America didnt vote for BO; hence
|
| the Obama coalition. Black and brown people also voted in larger numbers because
|
| it was a history making election, BLACK man running for, and having a good chance
|
| to become president in a country whose history and riches is built on white supremacy. They
|
| didnt come out in the same numbers afterwards, hence he lost control of the congress. But
|
| yes, lets try to paint black (and brown) peoples with the same racist brush; let''s
|
| pretend that black people having ''racial'' bias is the same as white racists
|
| who own the systems; lets pretend they have the power to impact the lives of whites
|
| in the same way; let''s pretend that a black trump would have been elected to
|
| the presidency.'
|
| - source_sentence: 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: You are picking fly shit out of pepper.'
|
| sentences:
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: Sounds like that''s pretty close to what Governor Walker will submit to
|
| the lege in early October. They can once again try to avoid making the difficult
|
| decisions before November 8 but the pressure and the spotlight will be on them
|
| to do their damn jobs now that the Chenault/Meyers caucus has refused to deal
|
| with what the Governor proposed last session.'
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: The write references time some the damn was built. When land was stolen
|
| and a group of people were banned from the city. This happened and it was recent.
|
| Very predictable that such treatment by pioneers would be forgiven. In fact some
|
| folk don''t even want such history even spoke of. The behavior of Anchorage''s
|
| pioneers is real and horrible. And recent. But hey, go ahead and dimish that horrible
|
| behavior with info from the Amazon. It speaks volumes about how folks view the
|
| heinous behaviors of our pioneers.'
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: They deserve the death penalty, why should we pay for their home away from
|
| home for the rest of their lives, pretty pathetic 😞'
|
| - source_sentence: 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: We will see women as popes when Islamic men stop raping women, playing
|
| tahharush, killing gays, forcing them to cover up, not allowing them to drive,
|
| stop performing genital mutilation etc. Jk we know neither will ever happen. Now
|
| run along and make my white self a sandwich honey!!'
|
| sentences:
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: Right, so instead of proving your claim about the Hawaiian haters in this
|
| thread, you instead respond with the typical racist Hawaiian stereotypes about
|
| haoles.
|
|
|
|
|
| I see racism in Hawaii because ignorant racists like you pretend that your blind
|
| hatred is something other than what it is.
|
|
|
|
|
| The fact is I have said nothing different than the kanaka maoil who were arrested
|
| outside of the Na''i Aupuni convention, but the difference is, you can not stand
|
| hearing it from someone who you assume does not have the magic blood.
|
|
|
|
|
| News flash. Every single person on this planet is indigenous. Get over yourself.'
|
| - 'Instruct: Retrieve semantically similar text based on safety profile
|
|
|
| Query: Gary Johnson.......Really? Gary should endorse Trump to prevent Hillary
|
| from winning. I say DAMN the media lies! Clintons Out of our government! Podesta
|
| and all the other little rats too!'
|
| - "Instruct: Retrieve semantically similar text based on safety profile\nQuery:\
|
| \ It's official. Canadians have been driven to mental illness. \n\n(The test for\
|
| \ civility here is confusing. I rated a comment referring to the left as disgusting\
|
| \ and vile as not good but civil. There were no personal names. \"Vile\" means\
|
| \ disgusted, and the poster was disgusted. So ??? If that's not OK, why is \"\
|
| Fiberals\" allowed? That's referring to the Liberals as liars.)"
|
| pipeline_tag: sentence-similarity
|
| library_name: sentence-transformers
|
| ---
|
|
|
| # SentenceTransformer based on lightonai/modernbert-embed-large
|
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [lightonai/modernbert-embed-large](https://huggingface.co/lightonai/modernbert-embed-large). 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:** [lightonai/modernbert-embed-large](https://huggingface.co/lightonai/modernbert-embed-large) <!-- at revision 95a19bff4963b66d3c14fd4a20d147ebb4aaccfc -->
|
| - **Maximum Sequence Length:** 256 tokens
|
| - **Output Dimensionality:** 1024 dimensions
|
| - **Similarity Function:** Cosine Similarity
|
| <!-- - **Training Dataset:** Unknown -->
|
| <!-- - **Language:** Unknown -->
|
| <!-- - **License:** Unknown -->
|
|
|
| ### 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': 256, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
|
| (1): Pooling({'word_embedding_dimension': 1024, '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 = [
|
| 'Instruct: Retrieve semantically similar text based on safety profile\nQuery: We will see women as popes when Islamic men stop raping women, playing tahharush, killing gays, forcing them to cover up, not allowing them to drive, stop performing genital mutilation etc. Jk we know neither will ever happen. Now run along and make my white self a sandwich honey!!',
|
| 'Instruct: Retrieve semantically similar text based on safety profile\nQuery: It\'s official. Canadians have been driven to mental illness. \n\n(The test for civility here is confusing. I rated a comment referring to the left as disgusting and vile as not good but civil. There were no personal names. "Vile" means disgusted, and the poster was disgusted. So ??? If that\'s not OK, why is "Fiberals" allowed? That\'s referring to the Liberals as liars.)',
|
| "Instruct: Retrieve semantically similar text based on safety profile\nQuery: Right, so instead of proving your claim about the Hawaiian haters in this thread, you instead respond with the typical racist Hawaiian stereotypes about haoles.\n\nI see racism in Hawaii because ignorant racists like you pretend that your blind hatred is something other than what it is.\n\nThe fact is I have said nothing different than the kanaka maoil who were arrested outside of the Na'i Aupuni convention, but the difference is, you can not stand hearing it from someone who you assume does not have the magic blood.\n\nNews flash. Every single person on this planet is indigenous. Get over yourself.",
|
| ]
|
| embeddings = model.encode(sentences)
|
| print(embeddings.shape)
|
| # [3, 1024]
|
|
|
| # Get the similarity scores for the embeddings
|
| similarities = model.similarity(embeddings, embeddings)
|
| print(similarities)
|
| # tensor([[1.0000, 0.9453, 0.9609],
|
| # [0.9453, 1.0000, 0.9609],
|
| # [0.9609, 0.9609, 1.0000]], dtype=torch.bfloat16)
|
| ```
|
|
|
| <!--
|
| ### Direct Usage (Transformers)
|
|
|
| <details><summary>Click to see the direct usage in Transformers</summary>
|
|
|
| </details>
|
| -->
|
|
|
| <!--
|
| ### Downstream Usage (Sentence Transformers)
|
|
|
| You can finetune this model on your own dataset.
|
|
|
| <details><summary>Click to expand</summary>
|
|
|
| </details>
|
| -->
|
|
|
| <!--
|
| ### Out-of-Scope Use
|
|
|
| *List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| -->
|
|
|
| <!--
|
| ## Bias, Risks and Limitations
|
|
|
| *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| -->
|
|
|
| <!--
|
| ### Recommendations
|
|
|
| *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| -->
|
|
|
| ## Training Details
|
|
|
| ### Training Dataset
|
|
|
| #### Unnamed Dataset
|
|
|
| * Size: 12,868 training samples
|
| * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| * Approximate statistics based on the first 1000 samples:
|
| | | sentence_0 | sentence_1 | label |
|
| |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| | type | string | string | float |
|
| | details | <ul><li>min: 20 tokens</li><li>mean: 82.03 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 84.69 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.51</li><li>max: 1.0</li></ul> |
|
| * Samples:
|
| | sentence_0 | sentence_1 | label |
|
| |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
|
| | <code>Instruct: Retrieve semantically similar text based on safety profile<br>Query: You threatened to kill people when you made this statement. "Except maybe criminals who have to consider whether their next victim is packing heat. Which by the way, I don't. Probably." Too many of you white folks refuse to take responsibility for your choices. I consider the GOP, in the 21st century, to be little more than a white identity death cult. You love being white and armed more than being human beings or Americans. You have made it clear that you have no problem taking a human life. Do you support the state sponsored killing of unarmed black people? BTW, you didn't respond to my comments about the Vietnam war. Are you not brave?</code> | <code>Instruct: Retrieve semantically similar text based on safety profile<br>Query: Shoot the messenger--an ancient tradition.</code> | <code>1.0</code> |
|
| | <code>Instruct: Retrieve semantically similar text based on safety profile<br>Query: This land is OUR land, David. If Seneca wants to do logging, then do it on private land, the problem is they have over cut their private lands and now they want to get their greedy hands on the last of OUR public forests. I have a job, I have been working since I was eleven years old and am nearing retirement age. I have also been a volunteer for over 25 years working to help us transition our economy and consciousness to one that is truly sustainable. We are in the midst of the most devastating crisis humans have ever faced due to burning fossil fuels, deforestation, over fishing, pollution, chemical farming and over human population. We have created the sixth mass species extinction! Wake up, David and the rest of you who think working to protect our last wildlands- and the biosphere in general- is "wacko." What is "wacko" is those of you who are in denial of this global crisis. Face facts.</code> | <code>Instruct: Retrieve semantically similar text based on safety profile<br>Query: Well that's a new level of ineptitude. They literally didn't get their own memo. I'm sure it was entirely accidental...</code> | <code>1.0</code> |
|
| | <code>Instruct: Retrieve semantically similar text based on safety profile<br>Query: What's the matter? <br><br>Did he get too close to the truth for you by characterizing Trump as a rich narcissist, materialist, demagogue who doesn't really have any coherent ''program'' other than staying at the center of attention, expanding his family's wealth and influence, and being applauded by his core constituency?</code> | <code>Instruct: Retrieve semantically similar text based on safety profile<br>Query: He can get a translator. Trudeau just speaks nonsense in both.</code> | <code>1.0</code> |
|
| * Loss: <code>__main__.OptimizedContrastiveDistillationLoss</code>
|
|
|
| ### Training Hyperparameters
|
| #### Non-Default Hyperparameters
|
|
|
| - `per_device_train_batch_size`: 16
|
| - `per_device_eval_batch_size`: 16
|
| - `num_train_epochs`: 1
|
| - `multi_dataset_batch_sampler`: round_robin
|
|
|
| #### All Hyperparameters
|
| <details><summary>Click to expand</summary>
|
|
|
| - `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`: 1
|
| - `max_steps`: -1
|
| - `lr_scheduler_type`: linear
|
| - `lr_scheduler_kwargs`: None
|
| - `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`: 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}
|
| - `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`: {}
|
|
|
| </details>
|
|
|
| ### Training Logs
|
| | Epoch | Step | Training Loss |
|
| |:------:|:----:|:-------------:|
|
| | 0.6211 | 500 | 0.0186 |
|
|
|
|
|
| ### Framework Versions
|
| - Python: 3.14.4
|
| - Sentence Transformers: 5.1.0
|
| - Transformers: 4.57.6
|
| - PyTorch: 2.11.0+cu128
|
| - Accelerate: 1.13.0
|
| - Datasets: 4.8.4
|
| - Tokenizers: 0.22.2
|
|
|
| ## 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",
|
| }
|
| ```
|
|
|
| <!--
|
| ## Glossary
|
|
|
| *Clearly define terms in order to be accessible across audiences.*
|
| -->
|
|
|
| <!--
|
| ## Model Card Authors
|
|
|
| *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| -->
|
|
|
| <!--
|
| ## Model Card Contact
|
|
|
| *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| --> |
