Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "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
+}

README.md

@@ -0,0 +1,571 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:19244
+- loss:MultipleNegativesRankingLoss
+base_model: intfloat/multilingual-e5-large
+widget:
+- source_sentence: 'query: @user Alright we would both see eye to eye that contraception
+    is ethically better, correct? I would think the most hard‑line #catholics would
+    agree with that even though they don''t support it. So sentientce is your line?
+    There is proof sentientce at roughly 18 to 25 weeks.'
+  sentences:
+  - 'passage: title: Aggressive or Moderate Fluid Resuscitation in Acute Pancreatitis
+    abstract: Early aggressive hydration is widely recommended for the management
+    of acute pancreatitis, but evidence for this practice is limited.'
+  - 'passage: title: Imperfect Vaccination Can Enhance the Transmission of Highly
+    Virulent Pathogens abstract: Could some vaccines drive the evolution of more virulent
+    pathogens? Conventional wisdom is that natural selection will remove highly lethal
+    pathogens if host death greatly reduces transmission. Vaccines that keep hosts
+    alive but still allow transmission could thus allow very virulent strains to circulate
+    in a population. Here we show experimentally that immunization of chickens against
+    Marek''s disease virus enhances the fitness of more virulent strains, making it
+    possible for hyperpathogenic strains to transmit. Immunity elicited by direct
+    vaccination or by maternal vaccination prolongs host survival but does not prevent
+    infection, viral replication or transmission, thus extending the infectious periods
+    of strains otherwise too lethal to persist. Our data show that anti-disease vaccines
+    that do not prevent transmission can create conditions that promote the emergence
+    of pathogen strains that cause more severe disease in unvaccinated hosts.'
+  - 'passage: title: When is the Capacity for Sentience Acquired During Human Fetal
+    Development? abstract: The question of when the human fetus develops the capacity
+    for sentience is central to many contentious issues. The answer could and should
+    influence attitudes toward IVF and embryo experimentation, abortion, and fetal
+    and neonatal surgery. For the fetus to be described as sentient, the somatosensory
+    pathways from the periphery to the primary somatosensory region of the cerebral
+    cortex must be established and functional. Fetal behaviour is described and the
+    development of the underlying anatomical substrate and the chemical and electrical
+    pathways involved in the detection, transmission, and perception of somatosensory
+    stimuli are reviewed.It is concluded that the basic neuronal substrate required
+    to transmit somatosensory information develops by mid-gestation (18 to 25 weeks),
+    however, the functional capacity of the neural circuitry is limited by the immaturity
+    of the system. Thus, 18 to 25 weeks is considered the earliest stage at which
+    the lower boundary of sentience could be placed. At this stage of development,
+    however, there is little evidence for the central processing of somatosensory
+    information. Before 30 weeks gestational age, EEG activity is extremely limited
+    and somatosensory evoked potentials are immature, lacking components which correlate
+    with information processing within the cerebral cortex. Thus, 30 weeks is considered
+    a more plausible stage of fetal development at which the lower boundary for sentience
+    could be placed.'
+- source_sentence: 'query: @_Karl_F_ karl ein paar zahlen inzwischen dafür auch schon
+    kostspielig ... einige mit dem leben & einige verlor auch seine gesundheit ein...
+    magst nur hoffen, daß es nicht alle betroffen, die dazu mehrfach verpflichtet
+    & gezwungen wurden.'
+  sentences:
+  - 'passage: title: Health effects in COPD smokers who switch to electronic cigarettes:
+    a retrospective-prospective 3-year follow-up abstract: Health effects of electronic
+    cigarette (EC) use in patients with chronic obstructive pulmonary disease (COPD)
+    are largely unexplored.We present findings from a long-term prospective assessment
+    of respiratory parameters in a cohort of COPD patients who ceased or substantially
+    reduced conventional cigarette use with ECs.We prospectively re-evaluated COPD
+    exacerbations, spirometric indices, subjective assessments (using the COPD Assessment
+    Tool [CAT] scores), physical activity (measured by the 6-minute walk distance
+    [6MWD]), and conventional cigarette use in EC users with COPD who were retrospectively
+    assessed previously. Baseline measurements prior to switching to EC use were compared
+    to follow-up visits at 12, 24, and 36 months. Age- and sex-matched regularly smoking
+    COPD patients who were not using ECs were included as reference (control) group.Complete
+    data were available from 44 patients. Compared to baseline in the EC-user group,
+    there was a marked decline in the use of conventional cigarettes. Although there
+    was no change in lung function, significant improvements in COPD exacerbation
+    rates, CAT scores, and 6MWD were observed consistently in the EC user group over
+    the 3-year period (p<0.01). Similar findings were noted in COPD EC users who also
+    smoked conventional cigarettes ("dual users").The present study suggests that
+    EC use may ameliorate objective and subjective COPD outcomes and that the benefits
+    gained may persist long-term. EC use may reverse some of the harm resulting from
+    tobacco smoking in COPD patients.'
+  - 'passage: title: A Case Report: Multifocal Necrotizing Encephalitis and Myocarditis
+    after BNT162b2 mRNA Vaccination against COVID-19 abstract: The current report
+    presents the case of a 76-year-old man with Parkinson''s disease (PD) who died
+    three weeks after receiving his third COVID-19 vaccination. The patient was first
+    vaccinated in May 2021 with the ChAdOx1 nCov-19 vector vaccine, followed by two
+    doses of the BNT162b2 mRNA vaccine in July and December 2021. The family of the
+    deceased requested an autopsy due to ambiguous clinical signs before death. PD
+    was confirmed by post-mortem examinations. Furthermore, signs of aspiration pneumonia
+    and systemic arteriosclerosis were evident. However, histopathological analyses
+    of the brain uncovered previously unsuspected findings, including acute vasculitis
+    (predominantly lymphocytic) as well as multifocal necrotizing encephalitis of
+    unknown etiology with pronounced inflammation including glial and lymphocytic
+    reaction. In the heart, signs of chronic cardiomyopathy as well as mild acute
+    lympho-histiocytic myocarditis and vasculitis were present. Although there was
+    no history of COVID-19 for this patient, immunohistochemistry for SARS-CoV-2 antigens
+    (spike and nucleocapsid proteins) was performed. Surprisingly, only spike protein
+    but no nucleocapsid protein could be detected within the foci of inflammation
+    in both the brain and the heart, particularly in the endothelial cells of small
+    blood vessels. Since no nucleocapsid protein could be detected, the presence of
+    spike protein must be ascribed to vaccination rather than to viral infection.
+    The findings corroborate previous reports of encephalitis and myocarditis caused
+    by gene-based COVID-19 vaccines.'
+  - 'passage: title: Persistent warm Mediterranean surface waters during the Roman
+    period abstract: Abstract Reconstruction of last millennia Sea Surface Temperature
+    (SST) evolution is challenging due to the difficulty retrieving good resolution
+    marine records and to the several uncertainties in the available proxy tools.
+    In this regard, the Roman Period (1 CE to 500 CE) was particularly relevant in
+    the socio-cultural development of the Mediterranean region while its climatic
+    characteristics remain uncertain. Here we present a new SST reconstruction from
+    the Sicily Channel based in Mg/Ca ratios measured on the planktonic foraminifer
+    Globigerinoides ruber . This new record is framed in the context of other previously
+    published Mediterranean SST records from the Alboran Sea, Minorca Basin and Aegean
+    Sea and also compared to a north Hemisphere temperature reconstruction. The most
+    solid image that emerges of this trans-Mediterranean comparison is the persistent
+    regional occurrence of a distinct warm phase during the Roman Period. This record
+    comparison consistently shows the Roman as the warmest period of the last 2 kyr,
+    about 2 °C warmer than average values for the late centuries for the Sicily and
+    Western Mediterranean regions. After the Roman Period a general cooling trend
+    developed in the region with several minor oscillations. We hypothesis the potential
+    link between this Roman Climatic Optimum and the expansion and subsequent decline
+    of the Roman Empire.'
+- source_sentence: 'query: 4/ Trotzdem versäumten Sie es in mehreren Publikationen
+    mit Landt, einen relevanten Interessenkonflikt zu deklarieren. Markantestes Beispiel,
+    Ihre Publikation zum #PCR-Protokoll für den Nachweis von #SARSCoV2.'
+  sentences:
+  - 'passage: title: Cancer risk associated with simian virus 40 contaminated polio
+    vaccine. abstract: The presence of SV40 in monkey cell cultures used in the preparation
+    of the polio vaccine from 1955 through 1961 is well documented. Investigations
+    have consistently demonstrated the oncogenic behavior of SV40 in animal models.
+    Early epidemiologic studies were inadequate in demonstrating an increase in cancer
+    incidence associated with contaminated vaccine. Recently, investigators have provided
+    persuasive evidence that SV40 is present in human ependymomas, choroid plexus
+    tumors, bone tumors, and mesotheliomas, however, the etiologic role of the virus
+    in tumorigenesis has not been established.Using data from SEER, we analyzed the
+    incidence of brain tumors, bone tumors, and mesotheliomas from 1973-1993 and the
+    possible relationship of these tumors with the administration of the SV40 contaminated
+    vaccine.Our analysis indicates increased rates of ependymomas (37%), osteogenic
+    sarcomas (26%), other bone tumors (34%) and mesothelioma (90%) among those in
+    the exposed as compared to the unexposed birth cohort.These data suggest that
+    there may be an increased incidence of certain cancers among the 98 million persons
+    exposed to contaminated polio vaccine in the U.S.; further investigations are
+    clearly justified.'
+  - 'passage: title: Detection of 2019 novel coronavirus (2019-nCoV) by real-time
+    RT-PCR abstract: Background The ongoing outbreak of the recently emerged novel
+    coronavirus (2019-nCoV) poses a challenge for public health laboratories as virus
+    isolates are unavailable while there is growing evidence that the outbreak is
+    more widespread than initially thought, and international spread through travellers
+    does already occur. Aim We aimed to develop and deploy robust diagnostic methodology
+    for use in public health laboratory settings without having virus material available.
+    Methods Here we present a validated diagnostic workflow for 2019-nCoV, its design
+    relying on close genetic relatedness of 2019-nCoV with SARS coronavirus, making
+    use of synthetic nucleic acid technology. Results The workflow reliably detects
+    2019-nCoV, and further discriminates 2019-nCoV from SARS-CoV. Through coordination
+    between academic and public laboratories, we confirmed assay exclusivity based
+    on 297 original clinical specimens containing a full spectrum of human respiratory
+    viruses. Control material is made available through European Virus Archive – Global
+    (EVAg), a European Union infrastructure project. Conclusion The present study
+    demonstrates the enormous response capacity achieved through coordination of academic
+    and public laboratories in national and European research networks.'
+  - 'passage: title: The lifetime cost of driving a car abstract: The car is one of
+    the most expensive household consumer goods, yet there is a limited understanding
+    of its private (internal) and social (external) cost per vehicle-km, year, or
+    lifetime of driving. This paper provides an overview of 23 private and ten social
+    cost items, and assesses these for three popular car models in Germany for the
+    year 2020. Results confirm that motorists underestimate the full private costs
+    of car ownership, while policy makers and planners underestimate social costs.
+    For the typical German travel distance of 15,000 car kilometers per year, the
+    total lifetime cost of car ownership (50 years) ranges between €599,082 for an
+    Opel Corsa to €956,798 for a Mercedes GLC. The share of this cost born by society
+    is 41% (€4674 per year) for the Opel Corsa, and 29% (€5273 per year) for the Mercedes
+    GLC. Findings suggest that for low-income groups, private car ownership can represent
+    a cost equal to housing, consuming a large share of disposable income. This creates
+    complexities in perceptions of transport costs, the economic viability of alternative
+    transport modes, or the justification of taxes.'
+- source_sentence: 'query: Type 1 Diabetes Incidence and Risk in Children With a Diagnosis
+    of COVID-19 As adults we are meant to be shielding the children. We are letting
+    them down day by day'
+  sentences:
+  - 'passage: title: Persistence of neutralizing antibodies a year after SARS‐CoV‐2
+    infection in humans abstract: Abstract Most subjects develop antibodies to SARS‐CoV‐2
+    following infection. In order to estimate the duration of immunity induced by
+    SARS‐CoV‐2 it is important to understand for how long antibodies persist after
+    infection in humans. Here, we assessed the persistence of serum antibodies following
+    WT SARS‐CoV‐2 infection at 8 and 13 months after diagnosis in 367 individuals.
+    The SARS‐CoV‐2 spike IgG (S‐IgG) and nucleoprotein IgG (N‐IgG) concentrations
+    and the proportion of subjects with neutralizing antibodies (NAb) were assessed.
+    Moreover, the NAb titers among a smaller subset of participants ( n = 78) against
+    a WT virus (B) and variants of concern (VOCs): Alpha (B.1.1.7), Beta (B.1.351),
+    and Delta (B.1.617.2) were determined. We found that NAb against the WT virus
+    persisted in 89% and S‐IgG in 97% of subjects for at least 13 months after infection.
+    Only 36% had N‐IgG by 13 months. The mean S‐IgG concentrations declined from 8
+    to 13 months by less than one third; N‐IgG concentrations declined by two‐thirds.
+    Subjects with severe infection had markedly higher IgG and NAb levels and are
+    expected to remain seropositive for longer. Significantly lower NAb titers against
+    the variants compared to the WT virus, especially after a mild disease, suggests
+    reduced protection against VOCs.'
+  - 'passage: title: Metastasis and Immune Evasion from Extracellular cGAMP Hydrolysis
+    abstract: Abstract Cytosolic DNA is characteristic of chromosomally unstable metastatic
+    cancer cells, resulting in constitutive activation of the cGAS–STING innate immune
+    pathway. How tumors co-opt inflammatory signaling while evading immune surveillance
+    remains unknown. Here, we show that the ectonucleotidase ENPP1 promotes metastasis
+    by selectively degrading extracellular cGAMP, an immune-stimulatory metabolite
+    whose breakdown products include the immune suppressor adenosine. ENPP1 loss suppresses
+    metastasis, restores tumor immune infiltration, and potentiates response to immune
+    checkpoint blockade in a manner dependent on tumor cGAS and host STING. Conversely,
+    overexpression of wild-type ENPP1, but not an enzymatically weakened mutant, promotes
+    migration and metastasis, in part through the generation of extracellular adenosine,
+    and renders otherwise sensitive tumors completely resistant to immunotherapy.
+    In human cancers, ENPP1 expression correlates with reduced immune cell infiltration,
+    increased metastasis, and resistance to anti–PD-1/PD-L1 treatment. Thus, cGAMP
+    hydrolysis by ENPP1 enables chromosomally unstable tumors to transmute cGAS activation
+    into an immune-suppressive pathway. Significance: Chromosomal instability promotes
+    metastasis by generating chronic tumor inflammation. ENPP1 facilitates metastasis
+    and enables tumor cells to tolerate inflammation by hydrolyzing the immunotransmitter
+    cGAMP, preventing its transfer from cancer cells to immune cells. This article
+    is highlighted in the In This Issue feature, p. 995'
+  - 'passage: title: Type 1 Diabetes Incidence and Risk in Children With a Diagnosis
+    of COVID-19 abstract: This study used a population-based individual patient data
+    set that included diagnoses of COVID-19 to determine whether there was a temporal
+    association between COVID-19 and type 1 diabetes in children.'
+- source_sentence: 'query: @user It’s quite possibly the reverse (Pfizer @ 39%) “Our
+    data show that anti-disease vaccines that do not prevent transmission can create
+    conditions that promote the emergence of pathogen strains that cause more severe
+    disease in unvaccinated hosts” Source:'
+  sentences:
+  - 'passage: title: Experimental Assessment of Carbon Dioxide Content in Inhaled
+    Air With or Without Face Masks in Healthy Children abstract: This randomized clinical
+    trial measured inhaled and exhaled carbon dioxide in children with and without
+    face masks.'
+  - 'passage: title: Access to lifesaving medical resources for African countries:
+    COVID-19 testing and response, ethics, and politics abstract: Coronavirus disease
+    2019 (COVID-19) has revealed how strikingly unprepared the world is for a pandemic
+    and how easily viruses spread in our interconnected world. A governance crisis
+    is unfolding alongside the pandemic as health officials around the world compete
+    for access to scarce medical supplies. As governments of African countries, and
+    those in low-income and middle-income countries around the world, seek to avoid
+    potentially catastrophic epidemics and learn from what has worked in other countries,
+    testing and other medical resources are of concern.'
+  - 'passage: title: Imperfect Vaccination Can Enhance the Transmission of Highly
+    Virulent Pathogens abstract: Could some vaccines drive the evolution of more virulent
+    pathogens? Conventional wisdom is that natural selection will remove highly lethal
+    pathogens if host death greatly reduces transmission. Vaccines that keep hosts
+    alive but still allow transmission could thus allow very virulent strains to circulate
+    in a population. Here we show experimentally that immunization of chickens against
+    Marek''s disease virus enhances the fitness of more virulent strains, making it
+    possible for hyperpathogenic strains to transmit. Immunity elicited by direct
+    vaccination or by maternal vaccination prolongs host survival but does not prevent
+    infection, viral replication or transmission, thus extending the infectious periods
+    of strains otherwise too lethal to persist. Our data show that anti-disease vaccines
+    that do not prevent transmission can create conditions that promote the emergence
+    of pathogen strains that cause more severe disease in unvaccinated hosts.'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-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:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) <!-- at revision 3d7cfbdacd47fdda877c5cd8a79fbcc4f2a574f3 -->
+- **Maximum Sequence Length:** 512 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/huggingface/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, 'architecture': 'XLMRobertaModel'})
+  (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("Barakuga/me5-checkthat-task1")
+# Run inference
+sentences = [
+    'query: @user It’s quite possibly the reverse (Pfizer @ 39%) “Our data show that anti-disease vaccines that do not prevent transmission can create conditions that promote the emergence of pathogen strains that cause more severe disease in unvaccinated hosts” Source:',
+    "passage: title: Imperfect Vaccination Can Enhance the Transmission of Highly Virulent Pathogens abstract: Could some vaccines drive the evolution of more virulent pathogens? Conventional wisdom is that natural selection will remove highly lethal pathogens if host death greatly reduces transmission. Vaccines that keep hosts alive but still allow transmission could thus allow very virulent strains to circulate in a population. Here we show experimentally that immunization of chickens against Marek's disease virus enhances the fitness of more virulent strains, making it possible for hyperpathogenic strains to transmit. Immunity elicited by direct vaccination or by maternal vaccination prolongs host survival but does not prevent infection, viral replication or transmission, thus extending the infectious periods of strains otherwise too lethal to persist. Our data show that anti-disease vaccines that do not prevent transmission can create conditions that promote the emergence of pathogen strains that cause more severe disease in unvaccinated hosts.",
+    'passage: title: Access to lifesaving medical resources for African countries: COVID-19 testing and response, ethics, and politics abstract: Coronavirus disease 2019 (COVID-19) has revealed how strikingly unprepared the world is for a pandemic and how easily viruses spread in our interconnected world. A governance crisis is unfolding alongside the pandemic as health officials around the world compete for access to scarce medical supplies. As governments of African countries, and those in low-income and middle-income countries around the world, seek to avoid potentially catastrophic epidemics and learn from what has worked in other countries, testing and other medical resources are of concern.',
+]
+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,  0.7027, -0.0760],
+#         [ 0.7027,  1.0000, -0.0821],
+#         [-0.0760, -0.0821,  1.0000]])
+```
+
+<!--
+### 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: 19,244 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                          | sentence_1                                                                           |
+  |:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                               |
+  | details | <ul><li>min: 21 tokens</li><li>mean: 59.89 tokens</li><li>max: 134 tokens</li></ul> | <ul><li>min: 30 tokens</li><li>mean: 336.42 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                     | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>query: In what way will Language Modelers such as ChatGPT Impact Jobs and Sectors? by Edward W. Felten, Manav Raj, Robert Seamans :: SSRN</code>                                                                                                                         | <code>passage: title: How will Language Modelers like ChatGPT Affect Occupations and Industries? abstract: Recent dramatic increases in AI language modeling capabilities has led to many questions about the effect of these technologies on the economy. In this paper we present a methodology to systematically assess the extent to which occupations, industries and geographies are exposed to advances in AI language modeling capabilities. We find that the top occupations exposed to language modeling include telemarketers and a variety of post-secondary teachers such as English language and literature, foreign language and literature, and history teachers. We find the top industries exposed to advances in language modeling are legal services and securities, commodities, and investments. We also find a positive correlation between wages and exposure to AI language modeling.</code>                                                                                                                                    |
+  | <code>query: Spannende Studie zu #POTS. Sie verdeutlicht, was man ärztlich häufig wahrnimmt, nämlich dass die geistige Leistungsfähigkeit beim Sitzen und Stehen nachlässt. In diesem Fall waren Konzentration und Ausführungsfunktion gegen Kontrollen vermindert. 1/6</code> | <code>passage: title: Cognitive functioning in postural orthostatic tachycardia syndrome among different body positions: a prospective pilot study (POTSKog study) abstract: Approximately 96% of patients with postural orthostatic tachycardia syndrome (PoTS) report cognitive complaints. We investigated whether cognitive function is impaired during sitting and active standing in 30 patients with PoTS compared with 30 healthy controls (HCs) and whether it will improve with the counter manoeuvre of leg crossing.In this prospective pilot study, patients with PoTS were compared to HCs matched for age, sex, and educational level. Baseline data included norepinephrine plasma levels, autonomic testing and baseline cognitive function in a seated position [the Montreal Cognitive Assessment, the Leistungsprüfsystem (LPS) subtests 1 and 2, and the Test of Attentional Performance (TAP)]. Cognitive functioning was examined in a randomized order in supine, upright and upright legs crossed position. The prima...</code> |
+  | <code>query: We now know that Omicron is far from mild. In the unvaccinated it is equally lethal, while being more contagious, as other strains. Most children were and remain not vaccinated. We were aware that in winter 2021. And we know it now.</code>                   | <code>passage: title: Intrinsic and effective severity of COVID-19 cases infected with the ancestral strain and Omicron BA.2 variant in Hong Kong abstract: ABSTRACT Background Understanding severity of infections with SARS-CoV-2 and its variants is crucial to inform public health measures. Here we used COVID-19 patient data from Hong Kong to characterise the severity profile of COVID-19 and to examine factors associated with fatality of infection. Methods Time-varying and age-specific effective severity measured by case-hospitalization risk and hospitalization risk was estimated with all individual COVID-19 case data collected in Hong Kong from 23 January 2020 through to 26 October 2022 over six epidemic waves, in comparison with estimates of influenza A(H1N1)pdm09 during the 2009 pandemic. The intrinsic severity of Omicron BA.2 was compared with the estimate for the ancestral strain with the data from unvaccinated patients without previous infections. Factors potentially associated with the...</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 4
+- `per_device_eval_batch_size`: 4
+- `num_train_epochs`: 1
+- `fp16`: True
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 4
+- `per_device_eval_batch_size`: 4
+- `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`: None
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `enable_jit_checkpoint`: False
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `use_cpu`: False
+- `seed`: 42
+- `data_seed`: None
+- `bf16`: False
+- `fp16`: True
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: -1
+- `ddp_backend`: None
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `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
+- `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
+- `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_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `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
+- `use_cache`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.1039 | 500  | 0.1880        |
+| 0.2079 | 1000 | 0.1486        |
+| 0.3118 | 1500 | 0.1368        |
+| 0.4157 | 2000 | 0.1392        |
+| 0.5196 | 2500 | 0.1169        |
+| 0.6236 | 3000 | 0.1305        |
+| 0.7275 | 3500 | 0.1070        |
+| 0.8314 | 4000 | 0.1079        |
+| 0.9354 | 4500 | 0.1064        |
+
+
+### Framework Versions
+- Python: 3.12.13
+- Sentence Transformers: 5.3.0
+- Transformers: 5.0.0
+- PyTorch: 2.10.0+cu128
+- Accelerate: 1.13.0
+- Datasets: 4.0.0
+- 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{oord2019representationlearningcontrastivepredictive,
+      title={Representation Learning with Contrastive Predictive Coding},
+      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
+      year={2019},
+      eprint={1807.03748},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/1807.03748},
+}
+```
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "5.0.0",
+    "pytorch": "2.10.0+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae083d97adc0b051c7699c537f31b9123c8abfe67848980ca53986303b19ec88
+size 2239607120

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe715a86a37cd2b20e5eaeee8b22815bce65de676d1e0cd856114b59dab67fc
+size 16766387

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}