Upload mixer model for hotpotqa (trained on 2000 queries)
Browse files- .gitattributes +1 -0
- README.md +366 -0
- config.json +38 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- cross-encoder
|
| 5 |
+
- reranker
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- dataset_size:6000
|
| 8 |
+
- loss:BinaryCrossEntropyLoss
|
| 9 |
+
base_model: BAAI/bge-reranker-v2-m3
|
| 10 |
+
pipeline_tag: text-ranking
|
| 11 |
+
library_name: sentence-transformers
|
| 12 |
+
metrics:
|
| 13 |
+
- pearson
|
| 14 |
+
- spearman
|
| 15 |
+
model-index:
|
| 16 |
+
- name: CrossEncoder based on BAAI/bge-reranker-v2-m3
|
| 17 |
+
results:
|
| 18 |
+
- task:
|
| 19 |
+
type: cross-encoder-correlation
|
| 20 |
+
name: Cross Encoder Correlation
|
| 21 |
+
dataset:
|
| 22 |
+
name: validation
|
| 23 |
+
type: validation
|
| 24 |
+
metrics:
|
| 25 |
+
- type: pearson
|
| 26 |
+
value: 0.9415655154266356
|
| 27 |
+
name: Pearson
|
| 28 |
+
- type: spearman
|
| 29 |
+
value: 0.9227894304162081
|
| 30 |
+
name: Spearman
|
| 31 |
+
- task:
|
| 32 |
+
type: cross-encoder-correlation
|
| 33 |
+
name: Cross Encoder Correlation
|
| 34 |
+
dataset:
|
| 35 |
+
name: train subset
|
| 36 |
+
type: train_subset
|
| 37 |
+
metrics:
|
| 38 |
+
- type: pearson
|
| 39 |
+
value: 0.8466559759529986
|
| 40 |
+
name: Pearson
|
| 41 |
+
- type: spearman
|
| 42 |
+
value: 0.8645374463046961
|
| 43 |
+
name: Spearman
|
| 44 |
+
---
|
| 45 |
+
|
| 46 |
+
# CrossEncoder based on BAAI/bge-reranker-v2-m3
|
| 47 |
+
|
| 48 |
+
This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
|
| 49 |
+
|
| 50 |
+
## Model Details
|
| 51 |
+
|
| 52 |
+
### Model Description
|
| 53 |
+
- **Model Type:** Cross Encoder
|
| 54 |
+
- **Base model:** [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) <!-- at revision 953dc6f6f85a1b2dbfca4c34a2796e7dde08d41e -->
|
| 55 |
+
- **Maximum Sequence Length:** 1024 tokens
|
| 56 |
+
- **Number of Output Labels:** 1 label
|
| 57 |
+
<!-- - **Training Dataset:** Unknown -->
|
| 58 |
+
<!-- - **Language:** Unknown -->
|
| 59 |
+
<!-- - **License:** Unknown -->
|
| 60 |
+
|
| 61 |
+
### Model Sources
|
| 62 |
+
|
| 63 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 64 |
+
- **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
|
| 65 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
|
| 66 |
+
- **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
|
| 67 |
+
|
| 68 |
+
## Usage
|
| 69 |
+
|
| 70 |
+
### Direct Usage (Sentence Transformers)
|
| 71 |
+
|
| 72 |
+
First install the Sentence Transformers library:
|
| 73 |
+
|
| 74 |
+
```bash
|
| 75 |
+
pip install -U sentence-transformers
|
| 76 |
+
```
|
| 77 |
+
|
| 78 |
+
Then you can load this model and run inference.
|
| 79 |
+
```python
|
| 80 |
+
from sentence_transformers import CrossEncoder
|
| 81 |
+
|
| 82 |
+
# Download from the 🤗 Hub
|
| 83 |
+
model = CrossEncoder("cross_encoder_model_id")
|
| 84 |
+
# Get scores for pairs of texts
|
| 85 |
+
pairs = [
|
| 86 |
+
['Which American director is older, Lee Daniels or Barry Sonnenfeld?', 'Barry Sonnenfeld. Barry Sonnenfeld (born April 1, 1953) is an American filmmaker and television director. He worked as cinematographer for the Coen brothers, then later he directed films such as "The Addams Family" and its sequel, "Addams Family Values" along with the "Men in Black" trilogy, and the critically acclaimed "Get Shorty". Sonnenfeld has also had four collaborations with Will Smith.</s>Logan Lucky. Logan Lucky is a 2017 American heist comedy film directed by Steven Soderbergh, based on an original script written by unknown newcomer Rebecca Blunt. Soderbergh came out of retirement to direct the film and to distribute it independently through his own company Fingerprint Releasing. The film features an ensemble cast consisting of Channing Tatum, Adam Driver, Riley Keough, Daniel Craig, Seth MacFarlane, Katie Holmes, Hilary Swank, Katherine Waterston and Sebastian Stan, and follows the unlucky Logan family who plan to rob the Charlotte Motor Speedway, and try to avoid getting caught by the FBI.</s>Lee Daniels. Lee Louis Daniels (born December 24, 1959) is an American producer and director. He produced "Monster\'s Ball" and directed "Precious", which received six Academy Award nominations, including Best Director; it won two of the awards.'],
|
| 87 |
+
['Poitevin and Moscow Water Dog, are breeds of what?', "Poitevin (dog). The Poitevin, known as the Chien de Haut-Poitou until 1957, is a breed of dog used in hunting as a scenthound, from the province of Poitou. This predominantly pack hound was created in the 17th century specifically to hunt wolves.</s>Moscow Water Dog. The Moscow Water Dog, also known as the Moscow Diver, Moscow Retriever or Moskovsky Vodolaz, is a little-known dog breed derived from the Newfoundland, Caucasian Shepherd Dog and East European Shepherd. It is now extinct, but was used in the development of the Black Russian Terrier. The Moscow Water Dog was produced only by the Red Star Kennels, the state operated organization chartered to provide working dogs for the armed services.</s>Ryukyu Inu. The Ryukyu Ken (琉球犬 lit. Ryuukyuu Dog) is a medium-sized breed of dog that originates from Okinawa, Japan. It is Okinawa's only pedigree dog breed. It is a rare dog and is slowly declining in numbers. There were as few as 400 Ryukyu Inu as of 2015. Unlike dogs such as the Kai Ken, the Ryukyu is not protected by the Nihon Ken Hozonkai."],
|
| 88 |
+
['Are Max Green and John Cooper both American?', 'Russell Crowe. Russell Ira Crowe (born 7 April 1964) is an actor, film producer and musician. Although a New Zealand citizen, he has lived most of his life in Australia. He came to international attention for his role as the Roman General Maximus Decimus Meridius in the 2000 historical epic film "Gladiator", directed by Ridley Scott, for which Crowe won an Academy Award for Best Actor, a Broadcast Film Critics Association Award for Best Actor, an Empire Award for Best Actor and a London Film Critics Circle Award for Best Actor and 10 further nominations for best actor.</s>John Cooper (musician). John Landrum Cooper (born April 7, 1975), professionally credited as John L. Cooper, is an American musician, singer and songwriter. He has been the lead vocalist, bassist and co-founder of the Grammy-nominated American Christian rock band Skillet since 1996.</s>American Sniper. American Sniper is a 2014 American biographical war drama film directed by Clint Eastwood and written by Jason Hall. It is loosely based on the memoir "American Sniper: The Autobiography of the Most Lethal Sniper in U.S. Military History" (2012) by Chris Kyle, with Scott McEwen and Jim DeFelice. The film follows the life of Kyle, who became the deadliest marksman in U.S. military history with 255 kills from four tours in the Iraq War, 160 of which were officially confirmed by the Department of Defense. While Kyle was celebrated for his military successes, his tours of duty took a heavy toll on his personal and family life. The film was produced by Eastwood, Robert Lorenz, Andrew Lazar, Bradley Cooper, and Peter Morgan. It stars Cooper as Kyle and Sienna Miller as his wife Taya, with Luke Grimes, Jake McDorman, Cory Hardrict, Kevin Lacz, Navid Negahban, and Keir O\'Donnell in supporting roles.'],
|
| 89 |
+
['What is the name of the musician that appeared on Days of out lives and all my children?', 'Eddie Rabbitt. Edward Thomas Rabbitt (November 27, 1941 – May 7, 1998) was an American singer and songwriter. His career began as a songwriter in the late 1960s, springboarding to a recording career after composing hits such as "Kentucky Rain" for Elvis Presley in 1970 and "Pure Love" for Ronnie Milsap in 1974. Later in the 1970s, Rabbitt helped to develop the crossover-influenced sound of country music prevalent in the 1980s with such hits as "Suspicions" and "Every Which Way but Loose." His duets "Both to Each Other (Friends and Lovers)" and "You and I", with Juice Newton and Crystal Gayle respectively, later appeared on the soap operas "Days of Our Lives" and "All My Children".</s>Mariah Carey. Mariah Carey (born March 27, 1969 or 1970) is an American singer, songwriter, record producer, and actress. In 1990, she rose to fame with the release of "Vision of Love" from her eponymous debut album. The album produced four chart-topping singles in the US and began what would become a string of commercially successful albums which solidified the singer as Columbia Records\' highest selling act. Carey and Boyz II Men spent a record sixteen weeks atop the "Billboard" Hot 100 in 1995–1996 with "One Sweet Day," which remains the longest-running number-one song in US chart history. Following a contentious divorce from Sony Music head Tommy Mottola, Carey adopted a new image and traversed towards hip hop with the release of "Butterfly" (1997). In 1998, she was honored as the world\'s best-selling recording artist of the 1990s at the World Music Awards and subsequently named the best-selling female artist of the millennium in 2000.</s>Drinkin\' My Baby (Off My Mind). "Drinkin\' My Baby (Off My Mind)" is a song co-written and recorded by American country music artist Eddie Rabbitt. It was released in February 1976 as the first single from the album "Rocky Mountain Music". "Drinkin\' My Baby (Off My Mind)" was Eddie Rabbitt\'s fourth country hit and the first of fifteen solo number one country hits. The single stayed at number one a single week and spent a total twelve weeks on the country chart. It was written by Rabbitt and Even Stevens.'],
|
| 90 |
+
['The current WBO Asia Pacific Super Middleweight Champion made his debut film appearance in a movie directed by who?', "Vijender Singh. Vijender Singh Beniwal (born 29 October 1985), better known as Vijender Singh is an Indian professional boxer and the current WBO Asia Pacific Super Middleweight Champion and WBO Oriental Super Middleweight Champion from Kaluwas, Bhiwani district in Haryana. He was educated in his village, after which he received a bachelor's degree from a local college in Bhiwani. He practised boxing at the Bhiwani Boxing Club where coach Jagdish Singh recognised his talent and encouraged him to take up boxing. He was coached by the Indian Boxing Coach Jagdish Singh.</s>Million Dollar Arm. Million Dollar Arm is a 2014 American biographical sports drama film directed by Craig Gillespie and produced by Walt Disney Pictures from a screenplay written by Thomas McCarthy. The film is based on the true story of baseball pitchers Rinku Singh and Dinesh Patel who were discovered by sports agent J. B. Bernstein after winning a reality show competition.</s>Dan Henderson. Daniel Jeffery Henderson (born August 24, 1970) is an American former mixed martial artist and Olympic wrestler, who last competed as a middleweight in the Ultimate Fighting Championship. He was the last Strikeforce Light Heavyweight Champion and was the last Welterweight (80 kg ) and Middleweight (95 kg ) champion of Pride Fighting Championships. Additionally, Henderson was the Brazil Open '97 Tournament Champion, the UFC 17 Middleweight Tournament Champion, the Rings: King of Kings 1999 Tournament Champion and the Pride Weltwerweight Grand Prix Tournament Champion. During his career, Henderson also challenged for the UFC Middleweight Championship (2x), the UFC Light Heavyweight Championship and the Strikeforce Middleweight Championship. He was the first mixed martial artist to concurrently hold two titles in two different weight classes in a major MMA promotion. At the time of his retirement after UFC 204, he was the oldest fighter on the UFC roster. Known to be one of the greatest mixed martial artists of all time having defeated a total of seventeen MMA world champions across four major MMA promotions (UFC, PRIDE FC, Strikeforce, and RINGS)."],
|
| 91 |
+
]
|
| 92 |
+
scores = model.predict(pairs)
|
| 93 |
+
print(scores.shape)
|
| 94 |
+
# (5,)
|
| 95 |
+
|
| 96 |
+
# Or rank different texts based on similarity to a single text
|
| 97 |
+
ranks = model.rank(
|
| 98 |
+
'Which American director is older, Lee Daniels or Barry Sonnenfeld?',
|
| 99 |
+
[
|
| 100 |
+
'Barry Sonnenfeld. Barry Sonnenfeld (born April 1, 1953) is an American filmmaker and television director. He worked as cinematographer for the Coen brothers, then later he directed films such as "The Addams Family" and its sequel, "Addams Family Values" along with the "Men in Black" trilogy, and the critically acclaimed "Get Shorty". Sonnenfeld has also had four collaborations with Will Smith.</s>Logan Lucky. Logan Lucky is a 2017 American heist comedy film directed by Steven Soderbergh, based on an original script written by unknown newcomer Rebecca Blunt. Soderbergh came out of retirement to direct the film and to distribute it independently through his own company Fingerprint Releasing. The film features an ensemble cast consisting of Channing Tatum, Adam Driver, Riley Keough, Daniel Craig, Seth MacFarlane, Katie Holmes, Hilary Swank, Katherine Waterston and Sebastian Stan, and follows the unlucky Logan family who plan to rob the Charlotte Motor Speedway, and try to avoid getting caught by the FBI.</s>Lee Daniels. Lee Louis Daniels (born December 24, 1959) is an American producer and director. He produced "Monster\'s Ball" and directed "Precious", which received six Academy Award nominations, including Best Director; it won two of the awards.',
|
| 101 |
+
"Poitevin (dog). The Poitevin, known as the Chien de Haut-Poitou until 1957, is a breed of dog used in hunting as a scenthound, from the province of Poitou. This predominantly pack hound was created in the 17th century specifically to hunt wolves.</s>Moscow Water Dog. The Moscow Water Dog, also known as the Moscow Diver, Moscow Retriever or Moskovsky Vodolaz, is a little-known dog breed derived from the Newfoundland, Caucasian Shepherd Dog and East European Shepherd. It is now extinct, but was used in the development of the Black Russian Terrier. The Moscow Water Dog was produced only by the Red Star Kennels, the state operated organization chartered to provide working dogs for the armed services.</s>Ryukyu Inu. The Ryukyu Ken (琉球犬 lit. Ryuukyuu Dog) is a medium-sized breed of dog that originates from Okinawa, Japan. It is Okinawa's only pedigree dog breed. It is a rare dog and is slowly declining in numbers. There were as few as 400 Ryukyu Inu as of 2015. Unlike dogs such as the Kai Ken, the Ryukyu is not protected by the Nihon Ken Hozonkai.",
|
| 102 |
+
'Russell Crowe. Russell Ira Crowe (born 7 April 1964) is an actor, film producer and musician. Although a New Zealand citizen, he has lived most of his life in Australia. He came to international attention for his role as the Roman General Maximus Decimus Meridius in the 2000 historical epic film "Gladiator", directed by Ridley Scott, for which Crowe won an Academy Award for Best Actor, a Broadcast Film Critics Association Award for Best Actor, an Empire Award for Best Actor and a London Film Critics Circle Award for Best Actor and 10 further nominations for best actor.</s>John Cooper (musician). John Landrum Cooper (born April 7, 1975), professionally credited as John L. Cooper, is an American musician, singer and songwriter. He has been the lead vocalist, bassist and co-founder of the Grammy-nominated American Christian rock band Skillet since 1996.</s>American Sniper. American Sniper is a 2014 American biographical war drama film directed by Clint Eastwood and written by Jason Hall. It is loosely based on the memoir "American Sniper: The Autobiography of the Most Lethal Sniper in U.S. Military History" (2012) by Chris Kyle, with Scott McEwen and Jim DeFelice. The film follows the life of Kyle, who became the deadliest marksman in U.S. military history with 255 kills from four tours in the Iraq War, 160 of which were officially confirmed by the Department of Defense. While Kyle was celebrated for his military successes, his tours of duty took a heavy toll on his personal and family life. The film was produced by Eastwood, Robert Lorenz, Andrew Lazar, Bradley Cooper, and Peter Morgan. It stars Cooper as Kyle and Sienna Miller as his wife Taya, with Luke Grimes, Jake McDorman, Cory Hardrict, Kevin Lacz, Navid Negahban, and Keir O\'Donnell in supporting roles.',
|
| 103 |
+
'Eddie Rabbitt. Edward Thomas Rabbitt (November 27, 1941 – May 7, 1998) was an American singer and songwriter. His career began as a songwriter in the late 1960s, springboarding to a recording career after composing hits such as "Kentucky Rain" for Elvis Presley in 1970 and "Pure Love" for Ronnie Milsap in 1974. Later in the 1970s, Rabbitt helped to develop the crossover-influenced sound of country music prevalent in the 1980s with such hits as "Suspicions" and "Every Which Way but Loose." His duets "Both to Each Other (Friends and Lovers)" and "You and I", with Juice Newton and Crystal Gayle respectively, later appeared on the soap operas "Days of Our Lives" and "All My Children".</s>Mariah Carey. Mariah Carey (born March 27, 1969 or 1970) is an American singer, songwriter, record producer, and actress. In 1990, she rose to fame with the release of "Vision of Love" from her eponymous debut album. The album produced four chart-topping singles in the US and began what would become a string of commercially successful albums which solidified the singer as Columbia Records\' highest selling act. Carey and Boyz II Men spent a record sixteen weeks atop the "Billboard" Hot 100 in 1995–1996 with "One Sweet Day," which remains the longest-running number-one song in US chart history. Following a contentious divorce from Sony Music head Tommy Mottola, Carey adopted a new image and traversed towards hip hop with the release of "Butterfly" (1997). In 1998, she was honored as the world\'s best-selling recording artist of the 1990s at the World Music Awards and subsequently named the best-selling female artist of the millennium in 2000.</s>Drinkin\' My Baby (Off My Mind). "Drinkin\' My Baby (Off My Mind)" is a song co-written and recorded by American country music artist Eddie Rabbitt. It was released in February 1976 as the first single from the album "Rocky Mountain Music". "Drinkin\' My Baby (Off My Mind)" was Eddie Rabbitt\'s fourth country hit and the first of fifteen solo number one country hits. The single stayed at number one a single week and spent a total twelve weeks on the country chart. It was written by Rabbitt and Even Stevens.',
|
| 104 |
+
"Vijender Singh. Vijender Singh Beniwal (born 29 October 1985), better known as Vijender Singh is an Indian professional boxer and the current WBO Asia Pacific Super Middleweight Champion and WBO Oriental Super Middleweight Champion from Kaluwas, Bhiwani district in Haryana. He was educated in his village, after which he received a bachelor's degree from a local college in Bhiwani. He practised boxing at the Bhiwani Boxing Club where coach Jagdish Singh recognised his talent and encouraged him to take up boxing. He was coached by the Indian Boxing Coach Jagdish Singh.</s>Million Dollar Arm. Million Dollar Arm is a 2014 American biographical sports drama film directed by Craig Gillespie and produced by Walt Disney Pictures from a screenplay written by Thomas McCarthy. The film is based on the true story of baseball pitchers Rinku Singh and Dinesh Patel who were discovered by sports agent J. B. Bernstein after winning a reality show competition.</s>Dan Henderson. Daniel Jeffery Henderson (born August 24, 1970) is an American former mixed martial artist and Olympic wrestler, who last competed as a middleweight in the Ultimate Fighting Championship. He was the last Strikeforce Light Heavyweight Champion and was the last Welterweight (80 kg ) and Middleweight (95 kg ) champion of Pride Fighting Championships. Additionally, Henderson was the Brazil Open '97 Tournament Champion, the UFC 17 Middleweight Tournament Champion, the Rings: King of Kings 1999 Tournament Champion and the Pride Weltwerweight Grand Prix Tournament Champion. During his career, Henderson also challenged for the UFC Middleweight Championship (2x), the UFC Light Heavyweight Championship and the Strikeforce Middleweight Championship. He was the first mixed martial artist to concurrently hold two titles in two different weight classes in a major MMA promotion. At the time of his retirement after UFC 204, he was the oldest fighter on the UFC roster. Known to be one of the greatest mixed martial artists of all time having defeated a total of seventeen MMA world champions across four major MMA promotions (UFC, PRIDE FC, Strikeforce, and RINGS).",
|
| 105 |
+
]
|
| 106 |
+
)
|
| 107 |
+
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
|
| 108 |
+
```
|
| 109 |
+
|
| 110 |
+
<!--
|
| 111 |
+
### Direct Usage (Transformers)
|
| 112 |
+
|
| 113 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 114 |
+
|
| 115 |
+
</details>
|
| 116 |
+
-->
|
| 117 |
+
|
| 118 |
+
<!--
|
| 119 |
+
### Downstream Usage (Sentence Transformers)
|
| 120 |
+
|
| 121 |
+
You can finetune this model on your own dataset.
|
| 122 |
+
|
| 123 |
+
<details><summary>Click to expand</summary>
|
| 124 |
+
|
| 125 |
+
</details>
|
| 126 |
+
-->
|
| 127 |
+
|
| 128 |
+
<!--
|
| 129 |
+
### Out-of-Scope Use
|
| 130 |
+
|
| 131 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 132 |
+
-->
|
| 133 |
+
|
| 134 |
+
## Evaluation
|
| 135 |
+
|
| 136 |
+
### Metrics
|
| 137 |
+
|
| 138 |
+
#### Cross Encoder Correlation
|
| 139 |
+
|
| 140 |
+
* Datasets: `validation` and `train_subset`
|
| 141 |
+
* Evaluated with [<code>CECorrelationEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CECorrelationEvaluator)
|
| 142 |
+
|
| 143 |
+
| Metric | validation | train_subset |
|
| 144 |
+
|:-------------|:-----------|:-------------|
|
| 145 |
+
| pearson | 0.9416 | 0.8467 |
|
| 146 |
+
| **spearman** | **0.9228** | **0.8645** |
|
| 147 |
+
|
| 148 |
+
<!--
|
| 149 |
+
## Bias, Risks and Limitations
|
| 150 |
+
|
| 151 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 152 |
+
-->
|
| 153 |
+
|
| 154 |
+
<!--
|
| 155 |
+
### Recommendations
|
| 156 |
+
|
| 157 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 158 |
+
-->
|
| 159 |
+
|
| 160 |
+
## Training Details
|
| 161 |
+
|
| 162 |
+
### Training Dataset
|
| 163 |
+
|
| 164 |
+
#### Unnamed Dataset
|
| 165 |
+
|
| 166 |
+
* Size: 6,000 training samples
|
| 167 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 168 |
+
* Approximate statistics based on the first 1000 samples:
|
| 169 |
+
| | sentence_0 | sentence_1 | label |
|
| 170 |
+
|:--------|:-------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
| 171 |
+
| type | string | string | float |
|
| 172 |
+
| details | <ul><li>min: 22 characters</li><li>mean: 101.02 characters</li><li>max: 486 characters</li></ul> | <ul><li>min: 473 characters</li><li>mean: 1734.37 characters</li><li>max: 4615 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> |
|
| 173 |
+
* Samples:
|
| 174 |
+
| sentence_0 | sentence_1 | label |
|
| 175 |
+
|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
|
| 176 |
+
| <code>Which American director is older, Lee Daniels or Barry Sonnenfeld?</code> | <code>Barry Sonnenfeld. Barry Sonnenfeld (born April 1, 1953) is an American filmmaker and television director. He worked as cinematographer for the Coen brothers, then later he directed films such as "The Addams Family" and its sequel, "Addams Family Values" along with the "Men in Black" trilogy, and the critically acclaimed "Get Shorty". Sonnenfeld has also had four collaborations with Will Smith.</s>Logan Lucky. Logan Lucky is a 2017 American heist comedy film directed by Steven Soderbergh, based on an original script written by unknown newcomer Rebecca Blunt. Soderbergh came out of retirement to direct the film and to distribute it independently through his own company Fingerprint Releasing. The film features an ensemble cast consisting of Channing Tatum, Adam Driver, Riley Keough, Daniel Craig, Seth MacFarlane, Katie Holmes, Hilary Swank, Katherine Waterston and Sebastian Stan, and follows the unlucky Logan family who plan to rob the Charlotte Motor Speedway, and try to avoid gettin...</code> | <code>1.0</code> |
|
| 177 |
+
| <code>Poitevin and Moscow Water Dog, are breeds of what?</code> | <code>Poitevin (dog). The Poitevin, known as the Chien de Haut-Poitou until 1957, is a breed of dog used in hunting as a scenthound, from the province of Poitou. This predominantly pack hound was created in the 17th century specifically to hunt wolves.</s>Moscow Water Dog. The Moscow Water Dog, also known as the Moscow Diver, Moscow Retriever or Moskovsky Vodolaz, is a little-known dog breed derived from the Newfoundland, Caucasian Shepherd Dog and East European Shepherd. It is now extinct, but was used in the development of the Black Russian Terrier. The Moscow Water Dog was produced only by the Red Star Kennels, the state operated organization chartered to provide working dogs for the armed services.</s>Ryukyu Inu. The Ryukyu Ken (琉球犬 lit. Ryuukyuu Dog) is a medium-sized breed of dog that originates from Okinawa, Japan. It is Okinawa's only pedigree dog breed. It is a rare dog and is slowly declining in numbers. There were as few as 400 Ryukyu Inu as of 2015. Unlike dogs such as t...</code> | <code>1.0</code> |
|
| 178 |
+
| <code>Are Max Green and John Cooper both American?</code> | <code>Russell Crowe. Russell Ira Crowe (born 7 April 1964) is an actor, film producer and musician. Although a New Zealand citizen, he has lived most of his life in Australia. He came to international attention for his role as the Roman General Maximus Decimus Meridius in the 2000 historical epic film "Gladiator", directed by Ridley Scott, for which Crowe won an Academy Award for Best Actor, a Broadcast Film Critics Association Award for Best Actor, an Empire Award for Best Actor and a London Film Critics Circle Award for Best Actor and 10 further nominations for best actor.</s>John Cooper (musician). John Landrum Cooper (born April 7, 1975), professionally credited as John L. Cooper, is an American musician, singer and songwriter. He has been the lead vocalist, bassist and co-founder of the Grammy-nominated American Christian rock band Skillet since 1996.</s>American Sniper. American Sniper is a 2014 American biographical war drama film directed by Clint Eastwood and written by Jason Hal...</code> | <code>0.5</code> |
|
| 179 |
+
* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
|
| 180 |
+
```json
|
| 181 |
+
{
|
| 182 |
+
"activation_fn": "torch.nn.modules.linear.Identity",
|
| 183 |
+
"pos_weight": null
|
| 184 |
+
}
|
| 185 |
+
```
|
| 186 |
+
|
| 187 |
+
### Training Hyperparameters
|
| 188 |
+
#### Non-Default Hyperparameters
|
| 189 |
+
|
| 190 |
+
- `eval_strategy`: steps
|
| 191 |
+
- `per_device_train_batch_size`: 2
|
| 192 |
+
- `per_device_eval_batch_size`: 2
|
| 193 |
+
|
| 194 |
+
#### All Hyperparameters
|
| 195 |
+
<details><summary>Click to expand</summary>
|
| 196 |
+
|
| 197 |
+
- `overwrite_output_dir`: False
|
| 198 |
+
- `do_predict`: False
|
| 199 |
+
- `eval_strategy`: steps
|
| 200 |
+
- `prediction_loss_only`: True
|
| 201 |
+
- `per_device_train_batch_size`: 2
|
| 202 |
+
- `per_device_eval_batch_size`: 2
|
| 203 |
+
- `per_gpu_train_batch_size`: None
|
| 204 |
+
- `per_gpu_eval_batch_size`: None
|
| 205 |
+
- `gradient_accumulation_steps`: 1
|
| 206 |
+
- `eval_accumulation_steps`: None
|
| 207 |
+
- `torch_empty_cache_steps`: None
|
| 208 |
+
- `learning_rate`: 5e-05
|
| 209 |
+
- `weight_decay`: 0.0
|
| 210 |
+
- `adam_beta1`: 0.9
|
| 211 |
+
- `adam_beta2`: 0.999
|
| 212 |
+
- `adam_epsilon`: 1e-08
|
| 213 |
+
- `max_grad_norm`: 1
|
| 214 |
+
- `num_train_epochs`: 3
|
| 215 |
+
- `max_steps`: -1
|
| 216 |
+
- `lr_scheduler_type`: linear
|
| 217 |
+
- `lr_scheduler_kwargs`: {}
|
| 218 |
+
- `warmup_ratio`: 0.0
|
| 219 |
+
- `warmup_steps`: 0
|
| 220 |
+
- `log_level`: passive
|
| 221 |
+
- `log_level_replica`: warning
|
| 222 |
+
- `log_on_each_node`: True
|
| 223 |
+
- `logging_nan_inf_filter`: True
|
| 224 |
+
- `save_safetensors`: True
|
| 225 |
+
- `save_on_each_node`: False
|
| 226 |
+
- `save_only_model`: False
|
| 227 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 228 |
+
- `no_cuda`: False
|
| 229 |
+
- `use_cpu`: False
|
| 230 |
+
- `use_mps_device`: False
|
| 231 |
+
- `seed`: 42
|
| 232 |
+
- `data_seed`: None
|
| 233 |
+
- `jit_mode_eval`: False
|
| 234 |
+
- `use_ipex`: False
|
| 235 |
+
- `bf16`: False
|
| 236 |
+
- `fp16`: False
|
| 237 |
+
- `fp16_opt_level`: O1
|
| 238 |
+
- `half_precision_backend`: auto
|
| 239 |
+
- `bf16_full_eval`: False
|
| 240 |
+
- `fp16_full_eval`: False
|
| 241 |
+
- `tf32`: None
|
| 242 |
+
- `local_rank`: 0
|
| 243 |
+
- `ddp_backend`: None
|
| 244 |
+
- `tpu_num_cores`: None
|
| 245 |
+
- `tpu_metrics_debug`: False
|
| 246 |
+
- `debug`: []
|
| 247 |
+
- `dataloader_drop_last`: False
|
| 248 |
+
- `dataloader_num_workers`: 0
|
| 249 |
+
- `dataloader_prefetch_factor`: None
|
| 250 |
+
- `past_index`: -1
|
| 251 |
+
- `disable_tqdm`: False
|
| 252 |
+
- `remove_unused_columns`: True
|
| 253 |
+
- `label_names`: None
|
| 254 |
+
- `load_best_model_at_end`: False
|
| 255 |
+
- `ignore_data_skip`: False
|
| 256 |
+
- `fsdp`: []
|
| 257 |
+
- `fsdp_min_num_params`: 0
|
| 258 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 259 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 260 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 261 |
+
- `deepspeed`: None
|
| 262 |
+
- `label_smoothing_factor`: 0.0
|
| 263 |
+
- `optim`: adamw_torch
|
| 264 |
+
- `optim_args`: None
|
| 265 |
+
- `adafactor`: False
|
| 266 |
+
- `group_by_length`: False
|
| 267 |
+
- `length_column_name`: length
|
| 268 |
+
- `ddp_find_unused_parameters`: None
|
| 269 |
+
- `ddp_bucket_cap_mb`: None
|
| 270 |
+
- `ddp_broadcast_buffers`: False
|
| 271 |
+
- `dataloader_pin_memory`: True
|
| 272 |
+
- `dataloader_persistent_workers`: False
|
| 273 |
+
- `skip_memory_metrics`: True
|
| 274 |
+
- `use_legacy_prediction_loop`: False
|
| 275 |
+
- `push_to_hub`: False
|
| 276 |
+
- `resume_from_checkpoint`: None
|
| 277 |
+
- `hub_model_id`: None
|
| 278 |
+
- `hub_strategy`: every_save
|
| 279 |
+
- `hub_private_repo`: False
|
| 280 |
+
- `hub_always_push`: False
|
| 281 |
+
- `gradient_checkpointing`: False
|
| 282 |
+
- `gradient_checkpointing_kwargs`: None
|
| 283 |
+
- `include_inputs_for_metrics`: False
|
| 284 |
+
- `eval_do_concat_batches`: True
|
| 285 |
+
- `fp16_backend`: auto
|
| 286 |
+
- `push_to_hub_model_id`: None
|
| 287 |
+
- `push_to_hub_organization`: None
|
| 288 |
+
- `mp_parameters`:
|
| 289 |
+
- `auto_find_batch_size`: False
|
| 290 |
+
- `full_determinism`: False
|
| 291 |
+
- `torchdynamo`: None
|
| 292 |
+
- `ray_scope`: last
|
| 293 |
+
- `ddp_timeout`: 1800
|
| 294 |
+
- `torch_compile`: False
|
| 295 |
+
- `torch_compile_backend`: None
|
| 296 |
+
- `torch_compile_mode`: None
|
| 297 |
+
- `dispatch_batches`: None
|
| 298 |
+
- `split_batches`: None
|
| 299 |
+
- `include_tokens_per_second`: False
|
| 300 |
+
- `include_num_input_tokens_seen`: False
|
| 301 |
+
- `neftune_noise_alpha`: None
|
| 302 |
+
- `optim_target_modules`: None
|
| 303 |
+
- `batch_eval_metrics`: False
|
| 304 |
+
- `eval_on_start`: False
|
| 305 |
+
- `eval_use_gather_object`: False
|
| 306 |
+
- `prompts`: None
|
| 307 |
+
- `batch_sampler`: batch_sampler
|
| 308 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 309 |
+
- `router_mapping`: {}
|
| 310 |
+
- `learning_rate_mapping`: {}
|
| 311 |
+
|
| 312 |
+
</details>
|
| 313 |
+
|
| 314 |
+
### Training Logs
|
| 315 |
+
| Epoch | Step | Training Loss | validation_spearman | train_subset_spearman |
|
| 316 |
+
|:------:|:----:|:-------------:|:-------------------:|:---------------------:|
|
| 317 |
+
| 0.0333 | 100 | - | 0.9213 | 0.8790 |
|
| 318 |
+
| 0.0667 | 200 | - | 0.9229 | 0.8640 |
|
| 319 |
+
| 0.1 | 300 | - | 0.9192 | 0.8632 |
|
| 320 |
+
| 0.1333 | 400 | - | 0.9228 | 0.8698 |
|
| 321 |
+
| 0.1667 | 500 | 0.5092 | 0.9228 | 0.8645 |
|
| 322 |
+
|
| 323 |
+
|
| 324 |
+
### Framework Versions
|
| 325 |
+
- Python: 3.11.13
|
| 326 |
+
- Sentence Transformers: 5.2.0
|
| 327 |
+
- Transformers: 4.44.2
|
| 328 |
+
- PyTorch: 2.9.1+cu128
|
| 329 |
+
- Accelerate: 1.12.0
|
| 330 |
+
- Datasets: 4.0.0
|
| 331 |
+
- Tokenizers: 0.19.1
|
| 332 |
+
|
| 333 |
+
## Citation
|
| 334 |
+
|
| 335 |
+
### BibTeX
|
| 336 |
+
|
| 337 |
+
#### Sentence Transformers
|
| 338 |
+
```bibtex
|
| 339 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 340 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 341 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 342 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 343 |
+
month = "11",
|
| 344 |
+
year = "2019",
|
| 345 |
+
publisher = "Association for Computational Linguistics",
|
| 346 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 347 |
+
}
|
| 348 |
+
```
|
| 349 |
+
|
| 350 |
+
<!--
|
| 351 |
+
## Glossary
|
| 352 |
+
|
| 353 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 354 |
+
-->
|
| 355 |
+
|
| 356 |
+
<!--
|
| 357 |
+
## Model Card Authors
|
| 358 |
+
|
| 359 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 360 |
+
-->
|
| 361 |
+
|
| 362 |
+
<!--
|
| 363 |
+
## Model Card Contact
|
| 364 |
+
|
| 365 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 366 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "BAAI/bge-reranker-v2-m3",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"max_position_embeddings": 8194,
|
| 23 |
+
"model_type": "xlm-roberta",
|
| 24 |
+
"num_attention_heads": 16,
|
| 25 |
+
"num_hidden_layers": 24,
|
| 26 |
+
"output_past": true,
|
| 27 |
+
"pad_token_id": 1,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"sentence_transformers": {
|
| 30 |
+
"activation_fn": "torch.nn.modules.activation.Sigmoid",
|
| 31 |
+
"version": "5.2.0"
|
| 32 |
+
},
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.44.2",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 250002
|
| 38 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc09c3425e67a298e198667299a0b17885f510086f63674609e08957845e1c31
|
| 3 |
+
size 2271071852
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f91308c39b72c5ebb9e84e1a711fa260cdabea5bc12429caaaa92371a151785
|
| 3 |
+
size 17083154
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 1024,
|
| 50 |
+
"pad_token": "<pad>",
|
| 51 |
+
"sep_token": "</s>",
|
| 52 |
+
"sp_model_kwargs": {},
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|