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": 768,
+    "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_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 768,
+    "out_features": 3072,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b1d898c07ac671c1eaa9e9058c5562a3503096d25250f949038c12b426a8b2
+size 9437272

3_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 3072,
+    "out_features": 768,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

3_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db911362cd321bd167705582fd38700bd4f6e91367cffd894d62aab7d0adf25
+size 9437272

README.md

@@ -0,0 +1,551 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:21473
+- loss:MultipleNegativesRankingLoss
+base_model: google/embeddinggemma-300m
+widget:
+- source_sentence: USGS reports all earthquakes below magnitude 8.0 this quarter
+  sentences:
+  - Megaquake by September 30? A "megaquake" is defined as an earthquake with a magnitude
+    of 8.0 or greater. This market will resolve to “Yes” if 1 or more earthquakes
+    with a magnitude of 8.0 or higher occur anywhere on Earth between July 30 and
+    September 30, 2025, 11:59 PM ET. Otherwise, this market will resolve to “No”.
+    The resolution source for this market is the United States Geological Survey (USGS)
+    Earthquake Hazards Program (https://earthquake.usgs.gov/earthquakes/browse/significant.php#sigdef).
+    If an earthquake of substantial size has occurred within this market's timeframe
+    but not yet appeared on the resolution source, this market may remain open until
+    October 7, 2025, 11:59 PM ET, or until the earthquake in question otherwise appears
+    on the resolution source. If such an earthquake has not appeared on the resolution
+    source by that date, another credible resolution source will be used. After a
+    qualifying earthquake is registered, this market will remain open for 24 hours
+    to account for any revisions to its recorded magnitude. After 24 hours, this market
+    will resolve according to the latest provided data.
+  - Will "Elio" Opening Weekend Box Office be less than $20m? This market will resolve
+    according to how much “Elio” (2025) will gross domestically on its opening weekend.
+    The “Box Office” https://www.the-numbers.com/movie/Elio(2025)#tab=box-office will
+    be used to resolve this market once the values for the 3-day opening weekend (June
+    20 - June 22) are final (i.e. not studio estimates). If the reported value falls
+    exactly between two brackets, then this market will resolve to the higher range
+    bracket. Please note, this market will resolve according to the The Numbers figures
+    provided under Weekend Box Office Performance for the 3-day weekend (which typically
+    includes Thursday's previews), regardless of whether domestic refers to only the
+    USA, or to USA and Canada, etc. If there is no final data available by June 30,
+    2025, 11:59 PM ET, another credible resolution source will be chosen.
+  - Researchers Explore Correlation Between Solar Activity and Seismic Events
+- source_sentence: VCT Americas Kickoff concludes with Team X
+  sentences:
+  - 'Will PNAS retract Dan Ariely’s 2012 paper on dishonesty by October 1, 2021? This
+    market will resolve to “Yes” if the Proceedings of the National Academy of Sciences
+    issues a formal retraction for Dan Ariely’s 2012 paper “Signing at the beginning
+    makes ethics salient and decreases dishonest self-reports in comparison to signing
+    at the end”, https://www.pnas.org/content/109/38/15197.short, on or before October
+    1, 2021, 11:59:59 PM ET. This retraction may be initiated by either PNAS or the
+    original authors of the article. Otherwise, this market will resolve to “No.”
+    Note: corrections and partial retractions will also resolve to “No.” Only a full
+    retraction of the article will count. The resolution source for this market will
+    be official announcements from the Proceedings of the National Academy of Science,
+    see here for a list of retractions https://www.pnas.org/retractions. In the event
+    of ambiguity in terms of the market outcome, the market will be resolved in good
+    faith at the sole discretion of the Markets Integrity Committee (MIC).'
+  - Emerging Valorant Rosters to Watch Ahead of 2025 VCT Events
+  - 'Will 2GAME Esports win the VCT 2025 Americas Kickoff? VCT 2025: Americas Kickoff
+    is scheduled to take place January 16 - February 8, 2025. Find more information
+    about the tournament here: liquipedia.net/valorant/VCT/2025/Americas_League/Kickoff.
+    This market will resolve to “Yes” if 2GAME Esports wins this tournament. Otherwise,
+    this market will resolve to “No”. If this team is eliminated from the competition
+    based on the official rules of the tournament, this market will resolve to “No”.
+    If the winner of VCT 2025: Americas Kickoff is not determined by February 31,
+    2025, 11:59 PM ET, this market will resolve to “No”. The primary resolution source
+    for this market is official information provided directly from the VCT (e.g.,
+    valorantesports.com/en-US) and official footage of the tournament. However, other
+    credible reporting may also be used.'
+- source_sentence: Japan’s Central Election Management Council announces Constitutional
+    Democratic Party leads in seats
+  sentences:
+  - 'MLB: Who will win Toronto Blue Jays v. Tampa Bay Rays, scheduled for August 2,
+    7:10 PM ET? In the upcoming MLB game scheduled for August 2, 7:10 PM ET: If the
+    Toronto Blue Jays win, this market will resolve to “Blue Jays”. If the Tampa Bay
+    Rays win, this market will resolve to “Rays”. If the game is not completed by
+    August 9 (11:59:59 PM ET), this market will resolve 50-50.'
+  - Will the Constitutional Democratic Party win the most seats in the 2024 Japanese
+    general election? Early general elections are scheduled to be held in Japan on
+    27 October 2024. This market will resolve to "Yes" if the Constitutional Democratic
+    Party (立憲民主党, Rikken-minshutō) controls a greater number of seats in the House
+    of Representatives of the National Diet of Japan than any other party after the
+    results of the 2024 Japanese general election are finalized. Otherwise, this market
+    will resolve to "No". If the results of this election aren't known by December
+    31, 2024, 11:59 PM ET, this market will resolve to "No". In the case of a tie
+    between this party and any other for the most seats controlled, this market will
+    resolve in favor of the party whose listed name comes first in alphabetical order
+    using the English translation version of party names. This market's resolution
+    will be based solely on the number of seats won by the listed party, not any coalition
+    or alliance of which it may be a part. The primary resolution source for this
+    market will be official information from the Japanese government, specifically
+    the Central Election Management Council. However, a consensus of credible media
+    reports will also suffice to resolve this market.
+  - Tokyo Hosts Annual Democracy Forum Highlighting Japan’s Political History
+- source_sentence: US Open official cancels Pegula versus Muchova semifinal match
+  sentences:
+  - 'US Open: Pegula vs. Muchova Jessica Pegula and Karolina Muchova are scheduled
+    to play each other in a semifinal matchup in the US Open Women’s Singles Tournament
+    on September 5, 2024, at 8:30 PM ET. This market will resolve to “Pegula” if Jessica
+    Pegula wins her match against Karolina Muchova in the semifinals of the US Open
+    Women’s Singles tournament. This market will resolve to “Muchova” if Karolina
+    Muchova wins her match against Jessica Pegula in the semifinals of the US Open
+    Women’s Singles tournament. If the match ends in a tie, is canceled, or delayed
+    beyond September 12, 2024, this market will resolve to 50-50. The primary resolution
+    source for this market will be official information from the US Open (ex: https://www.usopen.org/index.html)
+    including live footage, however a consensus of credible reporting may also be
+    used.'
+  - Megaquake in September? A "megaquake" is defined as an earthquake with a magnitude
+    of 8.0 or greater. This market will resolve to “Yes” if 1 or more earthquakes
+    with a magnitude of 8.0 or higher occur anywhere on earth between September 2
+    and September 30, 2024, 11:59 PM ET. Otherwise this market will resolve to “No”.
+    The resolution source for this market is the United States Geological Survey (USGS)
+    Earthquake hazards program (https://earthquake.usgs.gov/earthquakes/browse/significant.php#sigdef).
+    If an earthquake of substantial size has occurred within this market's timeframe
+    but not yet appeared on the resolution source, this market may remain open until
+    October 7, 2024, 11:59 PM ET, or until the earthquake in question otherwise appears
+    on the resolution source. If such an earthquake has not appeared on the resolution
+    source by that date, another credible resolution source will be used.
+  - Jessica Pegula Trains with New Coach Ahead of Upcoming Tennis Season
+- source_sentence: Binance adds $SMOLE to its spot crypto exchange
+  sentences:
+  - $SMOLE listed on Binance in March? This market will resolve to "Yes" if the crypto
+    token smolecoin ($SMOLE) is listed for spot purchase on Binance by March 31, 2024,
+    11:59 PM ET. Otherwise, this market will resolve to "No". The primary resolution
+    source for this market will be Binance, however a consensus of credible reporting
+    will also be used.
+  - 'Historical Overview: Binance’s Impact on Global Cryptocurrency Trading Since
+    2017'
+  - 'FDA approves PTC Therapeutics’ Vatiquinone for Friedreich’s ataxia? This market
+    will resolve to "Yes" if the U.S. Food and Drug Administration (FDA) grants full
+    or conditional approval for PTC Therapeutics’ Vatiquinone as a treatment for Friedreich’s
+    ataxia by August 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to
+    "No." An approval is defined as: For new drugs: FDA issuance of an approval letter
+    for a New Drug Application (NDA) or Biologics License Application (BLA) For already-marketed
+    drugs seeking new indications: FDA approval of a supplemental NDA (sNDA) or supplemental
+    BLA (sBLA) for the specific indication referenced For generic drugs: FDA approval
+    of an Abbreviated New Drug Application (ANDA) For biosimilars: FDA approval of
+    a 351(k) application The following constitute qualifying approvals: Standard approval
+    (traditional approval based on clinical benefit), Accelerated approval (based
+    on surrogate endpoints), Approval with Risk Evaluation and Mitigation Strategy
+    (REMS), Approval with restricted distribution or indication limitations, except
+    compassionate use/expanded access programs The following do not constitute qualifying
+    approvals: Approvable letters that require additional actions before approval
+    Tentative approvals pending patent or exclusivity expiration FDA requests for
+    additional information or studies Extension of Prescription Drug User Fee Amendments
+    dates Approval for compassionate use or expanded access programs only Approval
+    only for export or for use outside the United States Emergency Use Authorization
+    (EUA) without full approval Complete Response Letters (CRLs) indicating the application
+    cannot be approved in its current form This market will immediately resolve to
+    "No" if the FDA issues a Complete Response Letter (CRL) or explicitly declines
+    to approve the application. If the drug sponsor withdraws the application before
+    the end of the month, the market will resolve to "No" immediately. If the listed
+    drug is approved before the end of the month, the market will resolve to "Yes,"
+    regardless of potential Advisory Committee votes against approval or later withdrawal
+    of approval. Conditional approvals may include post-marketing requirements or
+    commitments and still qualify. The primary resolution source will be official
+    information from the FDA; however, a consensus of credible reporting will also
+    be used.'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+model-index:
+- name: SentenceTransformer based on google/embeddinggemma-300m
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: base eval
+      type: base_eval
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9233456254005432
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: test eval
+      type: test_eval
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9998137354850769
+      name: Cosine Accuracy
+---
+
+# SentenceTransformer based on google/embeddinggemma-300m
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m). It maps sentences & paragraphs to a 768-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:** [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 -->
+- **Maximum Sequence Length:** 2048 tokens
+- **Output Dimensionality:** 768 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': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
+  (1): Pooling({'word_embedding_dimension': 768, '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): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+  (4): 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("dkcodes/poly-headline")
+# Run inference
+queries = [
+    "Binance adds $SMOLE to its spot crypto exchange",
+]
+documents = [
+    '$SMOLE listed on Binance in March? This market will resolve to "Yes" if the crypto token smolecoin ($SMOLE) is listed for spot purchase on Binance by March 31, 2024, 11:59 PM ET. Otherwise, this market will resolve to "No". The primary resolution source for this market will be Binance, however a consensus of credible reporting will also be used.',
+    'Historical Overview: Binance’s Impact on Global Cryptocurrency Trading Since 2017',
+    'FDA approves PTC Therapeutics’ Vatiquinone for Friedreich’s ataxia? This market will resolve to "Yes" if the U.S. Food and Drug Administration (FDA) grants full or conditional approval for PTC Therapeutics’ Vatiquinone as a treatment for Friedreich’s ataxia by August 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No." An approval is defined as: For new drugs: FDA issuance of an approval letter for a New Drug Application (NDA) or Biologics License Application (BLA) For already-marketed drugs seeking new indications: FDA approval of a supplemental NDA (sNDA) or supplemental BLA (sBLA) for the specific indication referenced For generic drugs: FDA approval of an Abbreviated New Drug Application (ANDA) For biosimilars: FDA approval of a 351(k) application The following constitute qualifying approvals: Standard approval (traditional approval based on clinical benefit), Accelerated approval (based on surrogate endpoints), Approval with Risk Evaluation and Mitigation Strategy (REMS), Approval with restricted distribution or indication limitations, except compassionate use/expanded access programs The following do not constitute qualifying approvals: Approvable letters that require additional actions before approval Tentative approvals pending patent or exclusivity expiration FDA requests for additional information or studies Extension of Prescription Drug User Fee Amendments dates Approval for compassionate use or expanded access programs only Approval only for export or for use outside the United States Emergency Use Authorization (EUA) without full approval Complete Response Letters (CRLs) indicating the application cannot be approved in its current form This market will immediately resolve to "No" if the FDA issues a Complete Response Letter (CRL) or explicitly declines to approve the application. If the drug sponsor withdraws the application before the end of the month, the market will resolve to "No" immediately. If the listed drug is approved before the end of the month, the market will resolve to "Yes," regardless of potential Advisory Committee votes against approval or later withdrawal of approval. Conditional approvals may include post-marketing requirements or commitments and still qualify. The primary resolution source will be official information from the FDA; however, a consensus of credible reporting will also be used.',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 768] [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[     0.8807,     -0.0750,      0.0007]])
+```
+
+<!--
+### 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.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Triplet
+
+* Datasets: `base_eval` and `test_eval`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric              | base_eval  | test_eval  |
+|:--------------------|:-----------|:-----------|
+| **cosine_accuracy** | **0.9233** | **0.9998** |
+
+<!--
+## 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: 21,473 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                             | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                               | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 12.65 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 53 tokens</li><li>mean: 165.55 tokens</li><li>max: 573 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 14.39 tokens</li><li>max: 26 tokens</li></ul> |
+* Samples:
+  | anchor                                                                     | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                | negative                                                                    |
+  |:---------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------|
+  | <code>Katy Perry confirms relationship with Justin Trudeau publicly</code> | <code>Katy Perry and Justin Trudeau confirmed relationship by August 31? This market will resolve to "Yes" if Katy Perry and Justin Trudeau are confirmed to be in a romantic relationship by August 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No". Confirmation must come directly from Katy Perry or Justin Trudeau or their official representative(s), and may come through public statements, social media posts, etc.</code> | <code>Katy Perry Announces New Album Release Date Amid Busy Year</code>     |
+  | <code>Jalen Milroe selected with first overall pick in NFL Draft</code>    | <code>Will Jalen Milroe be drafted in the First Round? This market will resolve to "Yes" if Jalen Milroe, the QB from Alabama, is selected in the first round of the 2025 NFL Draft scheduled for for April 24, 2025, in Green Bay, Wisconsin. Otherwise, this market will resolve to "No". The resolution source will be the official broadcast of the 2025 NFL Draft.</code>                                                                          | <code>Expectations Rise for Quarterbacks Entering the 2025 NFL Draft</code> |
+  | <code>Robert F. Kennedy Jr. confirms endorsement of Donald Trump</code>    | <code>RFK Jr. endorses Trump before November? This market will resolve to "Yes" if Robert F. Kennedy Jr. announces that he will vote for Donald Trump or formally endorses Trump for President of the United States by October 31, 2024, 11:59 PM ET. Otherwise this market will resolve to "No". The resolution source for this market will be official information from Robert F. Kennedy Jr. or one of his representatives.</code>                   | <code>Donald Trump Addresses His Campaign Strategies in Latest Rally</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
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 5,369 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                            | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                              | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 12.79 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 51 tokens</li><li>mean: 166.5 tokens</li><li>max: 491 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 14.36 tokens</li><li>max: 25 tokens</li></ul> |
+* Samples:
+  | anchor                                                              | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | negative                                                                             |
+  |:--------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | <code>NOAA confirms average global temperature breaks record</code> | <code>Will August 2021 average global temperature be the highest August temperature on record? This is a market on whether the average global land and ocean surface temperature for August 2021 will be the highest August temperature since global records began in 1880. The resolution source for this market will be the Global Climate Report for August 2021, published by NOAA's National Centers for Environmental Information (https://www.ncdc.noaa.gov/sotc/global/2021). This market will resolve to “Yes” if, for the month of August 2021 averaged as a whole, global land and ocean surface temperature anomaly, as measured by U.S. National Oceanic and Atmospheric Administration, will be greater than 0.98°C (1.76°F) above the 20th century average of 15.6°C (60.1°F), and “No” otherwise. Past data for the month of August can be found here https://www.ncdc.noaa.gov/cag/global/time-series/globe/land_ocean/1/8/1880-2021. This market will resolve when data is first available for the month of August 2021. In ...</code> | <code>Scientists Discuss Long-Term Trends in Global Temperature Variability</code>   |
+  | <code>Mavericks overcome Celtics in overtime 23rd</code>            | <code>Will the Celtics or the Mavericks win their February 23rd matchup? This is a market on which team will win the February 23rd, 2021 matchup between the Boston Celtics and the Dallas Mavericks. In the event this game is delayed for whatever reason, the resolution of this market will be delayed until the game takes place. In the extraordinarily unlikely event the game is canceled altogether, the market will resolve to 50/50. In the event of overtime, this market will resolve to the eventual winner. Results of this market will be decided by official scores available on https://www.nba.com/.</code>                                                                                                                                                                                                                                                                                                                                                                                                                           | <code>NBA Analysts Discuss Rising Trends in Team Strategies Across the League</code> |
+  | <code>Lakers win Game 4 against Suns in playoff series</code>       | <code>Who will win Suns vs. Lakers: Game 4? This is a market on who will win in the First Round, Game 4, NBA Playoff matchup between the Phoenix Suns and the Los Angeles Lakers, scheduled to take place at 3:30 PM ET May 30, 2021. This market will resolve to “Suns” if the Phoenix Suns win, and “Lakers” if the Los Angeles Lakers win. If the match is postponed to a date on or before June 6, 2021, 3:30 PM ET, the same market conditions will apply. If the match is postponed to a date after June 6, 2021, 3:30 PM ET or cancelled altogether, the market will resolve 50-50. In the event of ambiguity in terms of the market outcome, the market will be resolved in good faith at the sole discretion of the Markets Integrity Committee (MIC).</code>                                                                                                                                                                                                                                                                                   | <code>Phoenix Suns Team Chemistry Highlighted in Postseason Analysis</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
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 32
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `prompts`: task: search result | query: 
+
+#### 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`: 32
+- `per_device_eval_batch_size`: 8
+- `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`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: 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
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: task: search result | query: 
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch | Step | base_eval_cosine_accuracy | test_eval_cosine_accuracy |
+|:-----:|:----:|:-------------------------:|:-------------------------:|
+| -1    | -1   | 0.9233                    | 0.9998                    |
+
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.1.2
+- Transformers: 4.57.0.dev0
+- PyTorch: 2.8.0+cu126
+- Accelerate: 1.11.0
+- Datasets: 4.0.0
+- 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}
+}
+```
+
+<!--
+## 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.*
+-->

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3TextModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 3,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 257,
+  "transformers_version": "4.57.0.dev0",
+  "use_bidirectional_attention": true,
+  "use_cache": true,
+  "vocab_size": 262144
+}

config_sentence_transformers.json

@@ -0,0 +1,26 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.57.0.dev0",
+    "pytorch": "2.8.0+cu126"
+  },
+  "prompts": {
+    "query": "task: search result | query: ",
+    "document": "title: none | text: ",
+    "BitextMining": "task: search result | query: ",
+    "Clustering": "task: clustering | query: ",
+    "Classification": "task: classification | query: ",
+    "InstructionRetrieval": "task: code retrieval | query: ",
+    "MultilabelClassification": "task: classification | query: ",
+    "PairClassification": "task: sentence similarity | query: ",
+    "Reranking": "task: search result | query: ",
+    "Retrieval": "task: search result | query: ",
+    "Retrieval-query": "task: search result | query: ",
+    "Retrieval-document": "title: none | text: ",
+    "STS": "task: sentence similarity | query: ",
+    "Summarization": "task: summarization | query: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2beb496f4d1e15a3a891c07adf1d2a1e5a2a8cdc927cdbd38595628161c1e7f1
+size 1211486072

modules.json

@@ -0,0 +1,32 @@
+[
+  {
+    "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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4",
+    "path": "4_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 2048,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216e2a79606fe879c9f17c529c71cd241338407fd5646b595ffd3c4b9ea1d503
+size 33385262

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074