Text Ranking
sentence-transformers
Safetensors
xlm-roberta
cross-encoder
reranker
Generated from Trainer
dataset_size:8000
loss:BinaryCrossEntropyLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use OloriBern/hotpotqa-hybrid-2000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use OloriBern/hotpotqa-hybrid-2000 with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("OloriBern/hotpotqa-hybrid-2000") query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Notebooks
- Google Colab
- Kaggle
Upload hybrid model for hotpotqa (trained on 2000 queries)
Browse files- README.md +51 -48
- config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -31,22 +31,22 @@ model-index:
|
|
| 31 |
value: 0.99
|
| 32 |
name: Accuracy
|
| 33 |
- type: accuracy_threshold
|
| 34 |
-
value: 0.
|
| 35 |
name: Accuracy Threshold
|
| 36 |
- type: f1
|
| 37 |
-
value: 0.
|
| 38 |
name: F1
|
| 39 |
- type: f1_threshold
|
| 40 |
-
value: 0.
|
| 41 |
name: F1 Threshold
|
| 42 |
- type: precision
|
| 43 |
-
value: 0.
|
| 44 |
name: Precision
|
| 45 |
- type: recall
|
| 46 |
-
value: 0.
|
| 47 |
name: Recall
|
| 48 |
- type: average_precision
|
| 49 |
-
value: 0.
|
| 50 |
name: Average Precision
|
| 51 |
- task:
|
| 52 |
type: cross-encoder-binary-classification
|
|
@@ -56,25 +56,25 @@ model-index:
|
|
| 56 |
type: train_subset
|
| 57 |
metrics:
|
| 58 |
- type: accuracy
|
| 59 |
-
value: 0.
|
| 60 |
name: Accuracy
|
| 61 |
- type: accuracy_threshold
|
| 62 |
-
value: 0.
|
| 63 |
name: Accuracy Threshold
|
| 64 |
- type: f1
|
| 65 |
-
value: 0.
|
| 66 |
name: F1
|
| 67 |
- type: f1_threshold
|
| 68 |
-
value: 0.
|
| 69 |
name: F1 Threshold
|
| 70 |
- type: precision
|
| 71 |
-
value: 0.
|
| 72 |
name: Precision
|
| 73 |
- type: recall
|
| 74 |
-
value: 0.
|
| 75 |
name: Recall
|
| 76 |
- type: average_precision
|
| 77 |
-
value: 0.
|
| 78 |
name: Average Precision
|
| 79 |
---
|
| 80 |
|
|
@@ -118,11 +118,11 @@ from sentence_transformers import CrossEncoder
|
|
| 118 |
model = CrossEncoder("cross_encoder_model_id")
|
| 119 |
# Get scores for pairs of texts
|
| 120 |
pairs = [
|
| 121 |
-
['
|
| 122 |
-
['
|
| 123 |
-
['What
|
| 124 |
-
['
|
| 125 |
-
['
|
| 126 |
]
|
| 127 |
scores = model.predict(pairs)
|
| 128 |
print(scores.shape)
|
|
@@ -130,13 +130,13 @@ print(scores.shape)
|
|
| 130 |
|
| 131 |
# Or rank different texts based on similarity to a single text
|
| 132 |
ranks = model.rank(
|
| 133 |
-
'
|
| 134 |
[
|
| 135 |
-
|
| 136 |
-
'
|
| 137 |
-
'
|
| 138 |
-
'
|
| 139 |
-
'
|
| 140 |
]
|
| 141 |
)
|
| 142 |
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
|
|
@@ -177,13 +177,13 @@ You can finetune this model on your own dataset.
|
|
| 177 |
|
| 178 |
| Metric | validation | train_subset |
|
| 179 |
|:----------------------|:-----------|:-------------|
|
| 180 |
-
| accuracy | 0.99 | 0.
|
| 181 |
-
| accuracy_threshold | 0.
|
| 182 |
-
| f1 | 0.99 | 0.
|
| 183 |
-
| f1_threshold | 0.
|
| 184 |
-
| precision | 0.
|
| 185 |
-
| recall | 0.
|
| 186 |
-
| **average_precision** | **0.
|
| 187 |
|
| 188 |
<!--
|
| 189 |
## Bias, Risks and Limitations
|
|
@@ -206,16 +206,16 @@ You can finetune this model on your own dataset.
|
|
| 206 |
* Size: 8,000 training samples
|
| 207 |
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 208 |
* Approximate statistics based on the first 1000 samples:
|
| 209 |
-
| | sentence_0 | sentence_1 | label
|
| 210 |
-
|:--------|:-------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
| 211 |
-
| type | string | string | float
|
| 212 |
-
| details | <ul><li>min:
|
| 213 |
* Samples:
|
| 214 |
-
| sentence_0
|
| 215 |
-
|:----------------------------------------------------------------------------------------------------------------------------------
|
| 216 |
-
| <code>
|
| 217 |
-
| <code>
|
| 218 |
-
| <code>What
|
| 219 |
* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
|
| 220 |
```json
|
| 221 |
{
|
|
@@ -352,19 +352,22 @@ You can finetune this model on your own dataset.
|
|
| 352 |
</details>
|
| 353 |
|
| 354 |
### Training Logs
|
| 355 |
-
| Epoch | Step | validation_average_precision | train_subset_average_precision |
|
| 356 |
-
|:-----:|:----:|:----------------------------:|:------------------------------:|
|
| 357 |
-
| 0.025 | 100 | 0.
|
| 358 |
-
| 0.05 | 200 | 0.
|
| 359 |
-
| 0.075 | 300 | 0.
|
| 360 |
-
| 0.1 | 400 | 0.
|
|
|
|
|
|
|
|
|
|
| 361 |
|
| 362 |
|
| 363 |
### Framework Versions
|
| 364 |
- Python: 3.11.13
|
| 365 |
-
- Sentence Transformers: 5.2.
|
| 366 |
- Transformers: 4.44.2
|
| 367 |
-
- PyTorch: 2.
|
| 368 |
- Accelerate: 1.12.0
|
| 369 |
- Datasets: 4.0.0
|
| 370 |
- Tokenizers: 0.19.1
|
|
|
|
| 31 |
value: 0.99
|
| 32 |
name: Accuracy
|
| 33 |
- type: accuracy_threshold
|
| 34 |
+
value: 0.0021620974875986576
|
| 35 |
name: Accuracy Threshold
|
| 36 |
- type: f1
|
| 37 |
+
value: 0.9900332225913622
|
| 38 |
name: F1
|
| 39 |
- type: f1_threshold
|
| 40 |
+
value: 0.0011168117634952068
|
| 41 |
name: F1 Threshold
|
| 42 |
- type: precision
|
| 43 |
+
value: 0.9867549668874173
|
| 44 |
name: Precision
|
| 45 |
- type: recall
|
| 46 |
+
value: 0.9933333333333333
|
| 47 |
name: Recall
|
| 48 |
- type: average_precision
|
| 49 |
+
value: 0.9995697171348688
|
| 50 |
name: Average Precision
|
| 51 |
- task:
|
| 52 |
type: cross-encoder-binary-classification
|
|
|
|
| 56 |
type: train_subset
|
| 57 |
metrics:
|
| 58 |
- type: accuracy
|
| 59 |
+
value: 0.926
|
| 60 |
name: Accuracy
|
| 61 |
- type: accuracy_threshold
|
| 62 |
+
value: 0.6817218065261841
|
| 63 |
name: Accuracy Threshold
|
| 64 |
- type: f1
|
| 65 |
+
value: 0.9270216962524654
|
| 66 |
name: F1
|
| 67 |
- type: f1_threshold
|
| 68 |
+
value: 0.007857910357415676
|
| 69 |
name: F1 Threshold
|
| 70 |
- type: precision
|
| 71 |
+
value: 0.9288537549407114
|
| 72 |
name: Precision
|
| 73 |
- type: recall
|
| 74 |
+
value: 0.9251968503937008
|
| 75 |
name: Recall
|
| 76 |
- type: average_precision
|
| 77 |
+
value: 0.9650983248932256
|
| 78 |
name: Average Precision
|
| 79 |
---
|
| 80 |
|
|
|
|
| 118 |
model = CrossEncoder("cross_encoder_model_id")
|
| 119 |
# Get scores for pairs of texts
|
| 120 |
pairs = [
|
| 121 |
+
['What nationality was the person whose music inspired the Folias Flute and Guitar Duo ?', 'Kenneth Ascher. Kenneth Lee "Kenny" Ascher (born October 26, 1944 in Washington, D.C.) is an American jazz pianist, composer, and arranger who is active in jazz, rock, classical, and musical theater genres — in live venues, recording studios, and cinema production. He is widely known for co-writing, with Paul Williams, "Rainbow Connection" from "The Muppet Movie". Both Williams and Ascher received Oscar nominations for the 1979 Academy Awards for Best Original Song ("Rainbow Connection") and Best Original Score ("The Muppet Movie" Soundtrack). The song was also nominated for the Golden Globes for "Best Original Song" that same year.'],
|
| 122 |
+
['Orff Schulwerk was developed by the composer who was best known for what cantata?', 'Isabel McNeill Carley. Isabel McNeill Carley (4 December 1918 – 14 July 2011) was a published writer, editor, composer and music teacher. She’s considered one of the leaders of the Orff Schulwerk when it began to take hold in the United States in the 1960s. As a co-founder of the American Orff-Schulwerk Association (AOSA), Carley contributed greatly to the organization’s beginnings, serving as a board member and magazine editor. Carley devoted much of her life to musical instruction, publishing a series of books titled Recorder Improvisation and Technique.'],
|
| 123 |
+
['What country does Pioneer Canal and Orleans Canal have in common?', 'Same-sex marriage in the Sixth Circuit. On April 28, 2015, the Supreme Court of the United States heard oral arguments for "Obergefell v. Hodges" (Ohio), which was consolidated with three other same-sex marriage cases from the other states in the Sixth Circuit: "Tanco v. Haslam" (Tennessee), "DeBoer v. Snyder" (Michigan), "Bourke v. Beshear" (Kentucky). On June 26, 2015 the Supreme Court reversed the Sixth Circuit\'s decision, paving the way for same-sex marriage to become legal in those states, and setting a precedent for the entire nation. All four states complied with the ruling the same day it was issued before the mandate was actually issued. Every state in the circuit had a district court ruling against their states\' ban, but they were eventually stayed pending appeal. The Sixth Circuit consists of Kentucky, Michigan, Ohio, and Tennessee. On August 6, 2014, the Sixth Circuit heard oral arguments for same-sex marriage cases from each state within the circuit. On November 6, 2014, the Sixth Circuit in a split 2-1 decision, upheld the states\' same-sex marriage bans, reversing the district courts\' rulings that struck them down. The Sixth Circuit was the first and only circuit court since the landmark ruling "United States v. Windsor" to uphold the constitutionality of states\' same-sex marriage bans which caused a circuit split.'],
|
| 124 |
+
['In what year was the actor who plays an anxious novelist in the movie Ruby Sparks born?', 'Rufus Sewell. Rufus Frederik Sewell ( ; born 29 October 1967) is an English actor. In film, he has appeared in Kenneth Branagh\'s rendition of "Hamlet" (1996) playing Fortinbras, "The Woodlanders", "Dangerous Beauty", "Dark City", "A Knight\'s Tale", "The Illusionist", "Tristan and Isolde", and "Martha, Meet Frank, Daniel and Laurence". On television, he starred as "Obergruppenführer" John Smith in "The Man in the High Castle", an Italian detective in the BBC\'s television series "Zen" (2011) and also appeared in the mini-series "The Pillars of the Earth" (2010). In 1993 he played the hero, Will Ladislaw, in the BBC\'s adaptation of George Eliot\'s "Middlemarch". In 2003, he appeared in the lead role in "". He starred in the CBS drama "Eleventh Hour", which was cancelled in April 2009. On stage, he originated the role of Septimus Hodge in Tom Stoppard\'s "Arcadia" and the role of Jan in Stoppard\'s "Rock \'n\' Roll"; the latter earned him an Olivier Award and a Tony Award nomination.'],
|
| 125 |
+
["Brent Ferrin Ashworth appeared on Beck's special show on collecting, along with a Las Vegas-based businessman and reality television personality who made $2,000 a week selling what?", 'Marlo Stanfield. Marlo Stanfield is a fictional character on the HBO television drama "The Wire", played by actor Jamie Hector. Stanfield is a young, ambitious, intelligent and extremely ruthless player and is head of the eponymous Stanfield Organization in the Baltimore drug trade. Marlo\'s organization starts out small-time, operating in the vacuum left by the Barksdale Organization, and rises to the top of the Baltimore drug trade fairly quickly. A repeated theme in Marlo\'s characterization is his demand for unconditional respect, which trumps all other concerns. He frequently orders the deaths of those who disrespect him or undermine his name on the streets, however unwittingly. He is arguably the most violent and ruthless of the drug kingpins portrayed in "The Wire"; In 2016, "Rolling Stone" ranked him #2 of their "40 Greatest TV Villains of All Time".'],
|
| 126 |
]
|
| 127 |
scores = model.predict(pairs)
|
| 128 |
print(scores.shape)
|
|
|
|
| 130 |
|
| 131 |
# Or rank different texts based on similarity to a single text
|
| 132 |
ranks = model.rank(
|
| 133 |
+
'What nationality was the person whose music inspired the Folias Flute and Guitar Duo ?',
|
| 134 |
[
|
| 135 |
+
'Kenneth Ascher. Kenneth Lee "Kenny" Ascher (born October 26, 1944 in Washington, D.C.) is an American jazz pianist, composer, and arranger who is active in jazz, rock, classical, and musical theater genres — in live venues, recording studios, and cinema production. He is widely known for co-writing, with Paul Williams, "Rainbow Connection" from "The Muppet Movie". Both Williams and Ascher received Oscar nominations for the 1979 Academy Awards for Best Original Song ("Rainbow Connection") and Best Original Score ("The Muppet Movie" Soundtrack). The song was also nominated for the Golden Globes for "Best Original Song" that same year.',
|
| 136 |
+
'Isabel McNeill Carley. Isabel McNeill Carley (4 December 1918 – 14 July 2011) was a published writer, editor, composer and music teacher. She’s considered one of the leaders of the Orff Schulwerk when it began to take hold in the United States in the 1960s. As a co-founder of the American Orff-Schulwerk Association (AOSA), Carley contributed greatly to the organization’s beginnings, serving as a board member and magazine editor. Carley devoted much of her life to musical instruction, publishing a series of books titled Recorder Improvisation and Technique.',
|
| 137 |
+
'Same-sex marriage in the Sixth Circuit. On April 28, 2015, the Supreme Court of the United States heard oral arguments for "Obergefell v. Hodges" (Ohio), which was consolidated with three other same-sex marriage cases from the other states in the Sixth Circuit: "Tanco v. Haslam" (Tennessee), "DeBoer v. Snyder" (Michigan), "Bourke v. Beshear" (Kentucky). On June 26, 2015 the Supreme Court reversed the Sixth Circuit\'s decision, paving the way for same-sex marriage to become legal in those states, and setting a precedent for the entire nation. All four states complied with the ruling the same day it was issued before the mandate was actually issued. Every state in the circuit had a district court ruling against their states\' ban, but they were eventually stayed pending appeal. The Sixth Circuit consists of Kentucky, Michigan, Ohio, and Tennessee. On August 6, 2014, the Sixth Circuit heard oral arguments for same-sex marriage cases from each state within the circuit. On November 6, 2014, the Sixth Circuit in a split 2-1 decision, upheld the states\' same-sex marriage bans, reversing the district courts\' rulings that struck them down. The Sixth Circuit was the first and only circuit court since the landmark ruling "United States v. Windsor" to uphold the constitutionality of states\' same-sex marriage bans which caused a circuit split.',
|
| 138 |
+
'Rufus Sewell. Rufus Frederik Sewell ( ; born 29 October 1967) is an English actor. In film, he has appeared in Kenneth Branagh\'s rendition of "Hamlet" (1996) playing Fortinbras, "The Woodlanders", "Dangerous Beauty", "Dark City", "A Knight\'s Tale", "The Illusionist", "Tristan and Isolde", and "Martha, Meet Frank, Daniel and Laurence". On television, he starred as "Obergruppenführer" John Smith in "The Man in the High Castle", an Italian detective in the BBC\'s television series "Zen" (2011) and also appeared in the mini-series "The Pillars of the Earth" (2010). In 1993 he played the hero, Will Ladislaw, in the BBC\'s adaptation of George Eliot\'s "Middlemarch". In 2003, he appeared in the lead role in "". He starred in the CBS drama "Eleventh Hour", which was cancelled in April 2009. On stage, he originated the role of Septimus Hodge in Tom Stoppard\'s "Arcadia" and the role of Jan in Stoppard\'s "Rock \'n\' Roll"; the latter earned him an Olivier Award and a Tony Award nomination.',
|
| 139 |
+
'Marlo Stanfield. Marlo Stanfield is a fictional character on the HBO television drama "The Wire", played by actor Jamie Hector. Stanfield is a young, ambitious, intelligent and extremely ruthless player and is head of the eponymous Stanfield Organization in the Baltimore drug trade. Marlo\'s organization starts out small-time, operating in the vacuum left by the Barksdale Organization, and rises to the top of the Baltimore drug trade fairly quickly. A repeated theme in Marlo\'s characterization is his demand for unconditional respect, which trumps all other concerns. He frequently orders the deaths of those who disrespect him or undermine his name on the streets, however unwittingly. He is arguably the most violent and ruthless of the drug kingpins portrayed in "The Wire"; In 2016, "Rolling Stone" ranked him #2 of their "40 Greatest TV Villains of All Time".',
|
| 140 |
]
|
| 141 |
)
|
| 142 |
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
|
|
|
|
| 177 |
|
| 178 |
| Metric | validation | train_subset |
|
| 179 |
|:----------------------|:-----------|:-------------|
|
| 180 |
+
| accuracy | 0.99 | 0.926 |
|
| 181 |
+
| accuracy_threshold | 0.0022 | 0.6817 |
|
| 182 |
+
| f1 | 0.99 | 0.927 |
|
| 183 |
+
| f1_threshold | 0.0011 | 0.0079 |
|
| 184 |
+
| precision | 0.9868 | 0.9289 |
|
| 185 |
+
| recall | 0.9933 | 0.9252 |
|
| 186 |
+
| **average_precision** | **0.9996** | **0.9651** |
|
| 187 |
|
| 188 |
<!--
|
| 189 |
## Bias, Risks and Limitations
|
|
|
|
| 206 |
* Size: 8,000 training samples
|
| 207 |
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 208 |
* Approximate statistics based on the first 1000 samples:
|
| 209 |
+
| | sentence_0 | sentence_1 | label |
|
| 210 |
+
|:--------|:-------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 211 |
+
| type | string | string | float |
|
| 212 |
+
| details | <ul><li>min: 35 characters</li><li>mean: 104.32 characters</li><li>max: 474 characters</li></ul> | <ul><li>min: 92 characters</li><li>mean: 537.42 characters</li><li>max: 2340 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.51</li><li>max: 1.0</li></ul> |
|
| 213 |
* Samples:
|
| 214 |
+
| sentence_0 | sentence_1 | label |
|
| 215 |
+
|:----------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
|
| 216 |
+
| <code>What nationality was the person whose music inspired the Folias Flute and Guitar Duo ?</code> | <code>Kenneth Ascher. Kenneth Lee "Kenny" Ascher (born October 26, 1944 in Washington, D.C.) is an American jazz pianist, composer, and arranger who is active in jazz, rock, classical, and musical theater genres — in live venues, recording studios, and cinema production. He is widely known for co-writing, with Paul Williams, "Rainbow Connection" from "The Muppet Movie". Both Williams and Ascher received Oscar nominations for the 1979 Academy Awards for Best Original Song ("Rainbow Connection") and Best Original Score ("The Muppet Movie" Soundtrack). The song was also nominated for the Golden Globes for "Best Original Song" that same year.</code> | <code>0.0</code> |
|
| 217 |
+
| <code>Orff Schulwerk was developed by the composer who was best known for what cantata?</code> | <code>Isabel McNeill Carley. Isabel McNeill Carley (4 December 1918 – 14 July 2011) was a published writer, editor, composer and music teacher. She’s considered one of the leaders of the Orff Schulwerk when it began to take hold in the United States in the 1960s. As a co-founder of the American Orff-Schulwerk Association (AOSA), Carley contributed greatly to the organization’s beginnings, serving as a board member and magazine editor. Carley devoted much of her life to musical instruction, publishing a series of books titled Recorder Improvisation and Technique.</code> | <code>0.0</code> |
|
| 218 |
+
| <code>What country does Pioneer Canal and Orleans Canal have in common?</code> | <code>Same-sex marriage in the Sixth Circuit. On April 28, 2015, the Supreme Court of the United States heard oral arguments for "Obergefell v. Hodges" (Ohio), which was consolidated with three other same-sex marriage cases from the other states in the Sixth Circuit: "Tanco v. Haslam" (Tennessee), "DeBoer v. Snyder" (Michigan), "Bourke v. Beshear" (Kentucky). On June 26, 2015 the Supreme Court reversed the Sixth Circuit's decision, paving the way for same-sex marriage to become legal in those states, and setting a precedent for the entire nation. All four states complied with the ruling the same day it was issued before the mandate was actually issued. Every state in the circuit had a district court ruling against their states' ban, but they were eventually stayed pending appeal. The Sixth Circuit consists of Kentucky, Michigan, Ohio, and Tennessee. On August 6, 2014, the Sixth Circuit heard oral arguments for same-sex marriage cases from each state within the circuit. On November 6, 2...</code> | <code>0.0</code> |
|
| 219 |
* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
|
| 220 |
```json
|
| 221 |
{
|
|
|
|
| 352 |
</details>
|
| 353 |
|
| 354 |
### Training Logs
|
| 355 |
+
| Epoch | Step | Training Loss | validation_average_precision | train_subset_average_precision |
|
| 356 |
+
|:-----:|:----:|:-------------:|:----------------------------:|:------------------------------:|
|
| 357 |
+
| 0.025 | 100 | - | 0.9988 | 0.9757 |
|
| 358 |
+
| 0.05 | 200 | - | 0.9992 | 0.9766 |
|
| 359 |
+
| 0.075 | 300 | - | 0.9997 | 0.9806 |
|
| 360 |
+
| 0.1 | 400 | - | 0.9997 | 0.8754 |
|
| 361 |
+
| 0.125 | 500 | 0.4041 | 0.9997 | 0.9600 |
|
| 362 |
+
| 0.15 | 600 | - | 0.9995 | 0.9732 |
|
| 363 |
+
| 0.175 | 700 | - | 0.9996 | 0.9651 |
|
| 364 |
|
| 365 |
|
| 366 |
### Framework Versions
|
| 367 |
- Python: 3.11.13
|
| 368 |
+
- Sentence Transformers: 5.2.2
|
| 369 |
- Transformers: 4.44.2
|
| 370 |
+
- PyTorch: 2.10.0+cu128
|
| 371 |
- Accelerate: 1.12.0
|
| 372 |
- Datasets: 4.0.0
|
| 373 |
- Tokenizers: 0.19.1
|
config.json
CHANGED
|
@@ -28,7 +28,7 @@
|
|
| 28 |
"position_embedding_type": "absolute",
|
| 29 |
"sentence_transformers": {
|
| 30 |
"activation_fn": "torch.nn.modules.activation.Sigmoid",
|
| 31 |
-
"version": "5.2.
|
| 32 |
},
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"transformers_version": "4.44.2",
|
|
|
|
| 28 |
"position_embedding_type": "absolute",
|
| 29 |
"sentence_transformers": {
|
| 30 |
"activation_fn": "torch.nn.modules.activation.Sigmoid",
|
| 31 |
+
"version": "5.2.2"
|
| 32 |
},
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"transformers_version": "4.44.2",
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2271071852
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32c6c440cedb9d2e88aa61031dd79dd7a0c56e29cd72b3c1c1bde9f225a0e292
|
| 3 |
size 2271071852
|