Datasets:

H-D-T
/

Buzz-slice-3-10-V1.2

conversations listlengths 2 21	source stringclasses 36 values	stack stringclasses 1 value
[ { "from": "human", "value": "Can you write short story and dialog about: Rashon asks to use Ajay's tractor because Rashon wants to be able to work on the farm" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Rashon asks to use Ajay's tractor because Rashon wants to be able ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being happy" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being happy\" could be:\n Tramaine's best friend is Alandra. He always knows how to make her laugh and is alway...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n to help another person" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"to help another person\" could be:\n Varun updates Brynnlee's software to the latest version because...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being upset" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being upset\" could be:\n Nico had his coat stolen. He felt upset because it was a gift from his grandparents a...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being ashamed" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being ashamed\" could be:\n Eren had run up a debt of a thousand dollars and now felt ashamed. He knew he nee...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you give me a short story description for this dialog?\n Lisset: Hey, dad.\n Dad: Hey, son. What's up?\n Lisset: Not much. Just thinking about some stuff.\n Dad: Like what?\n Lisset: Well, I was just thinking about how I should be responsible for my own actions. I alway...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being frustrated" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being frustrated\" could be:\n Katie stared at the lock, trying to remember the combination. He had writte...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being a criminal" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being a criminal\" could be:\n Kelton was arrested for shoplifting at the local grocery store. She was tak...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being disgusted" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being disgusted\" could be:\n Arnoldo sees how Zayn flirts with other guys and how she always has her phone...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n When Tessa wanted to find a new place to live, he put a notice up in his building's lobby. He described what he was looking for and asked people to contact him if they knew of any openings. Within a few days, he had several re...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n to make another person happy" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"to make another person happy\" could be:\n Nicolas is always looking for ways to make Daizy ha...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being becomes a better person" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being becomes a better person\" could be:\n Zenia realizes that his anger was misplaced and f...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n wanting to spend more time with another person" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"wanting to spend more time with another person\" could be:\n Savion worries ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog about: Lianne blames Micaiah for breaking a vase" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Lianne blames Micaiah for breaking a vase\" could be:\n Lianne blamed Micaiah for breaking a vase. She felt a...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n to make a difference" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"to make a difference\" could be:\n Christon gets on the radio to share his story about how he was able...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you give me a short story description for this dialog?\n Daliah: I think I might be drunk.\n Sarah: Yeah, you look it. What did you drink?\n Daliah: Just some beers. But I feel really dizzy and unsteady. And my vision is all blurry.\n Sarah: Well, that's to be expected w...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being a good reader" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being a good reader\" could be:\n Ryanna is a voracious reader. She consumes books with an insatiable a...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being gets angry" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being gets angry\" could be:\n Demarcus and Jaila were fighting over a present. Demarcus was angry because...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being refreshed" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being refreshed\" could be:\n Keenen was feeling sluggish and decided she needed a pick-me-up. She replaced...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n Arantza asked Olive to come with him because he wanted to spend some time together. He thought it would be fun to go get ice cream and then walk around the park." }, { "from": "gpt", "value": "Sure, a dialog for th...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being deceitful" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being deceitful\" could be:\n Jennings is a dishonest person. He says one thing but does another. For examp...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being brave" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being brave\" could be:\n Nariah discovered a secret that her best friend was keeping from her. She was brave e...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n to be prepared for a test" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"to be prepared for a test\" could be:\n Aliana reviews statistics because Aliana wants to be prep...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being happy" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being happy\" could be:\n Iker arranges the flowers in a tall vase. He feels happy when he is finished.\n Iker...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being cheated on" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being cheated on\" could be:\n Sianna meets a girl at a party and they start seeing each other casually. S...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog about: Kalayah goes to a new restaurant" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Kalayah goes to a new restaurant\" could be:\n Kalayah went to a new restaurant and was impressed by the food. The ste...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Alonso: Why did you say that to me?\n Oaklynn: I don't know, I was just mad.\n Alonso: Well, it wasn't very nice.\n Oaklynn: I'm sorry, okay? I didn't mean it.\n Alonso: You should be sorry. You made me really mad...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n Reyes sees a woman walking a dog. The woman is wearing a green dress and the dog is brown. Reyes feels excited because he loves dogs." }, { "from": "gpt", "value": "Sure, a dialog for this story could be:\n Reyes:...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being excited" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being excited\" could be:\n Selena writes a newspaper article. She is excited to share her story with the wor...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n wanting to cook for a living" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"wanting to cook for a living\" could be:\n Analeah is a gourmet chef who wants to cook for a l...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being reliable" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being reliable\" could be:\n Aarin is a dependable person who always follows through on his commitments. He ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Jaziyah: Sarah, I'm so frustrated right now. Everything seems to be setting me off and I can't help but lash out. I feel like I'm at boiling point and about to explode.\n Sarah: What's going on? What's got you so ups...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you give me a short story description for this dialog?\n Aseel: Why did you ruin my shirt? I loved that shirt!\n Little sister: I'm sorry, I didn't mean to. It was an accident.\n Aseel: Well, you should have been more careful! Now my shirt is ruined and it's all your faul...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n to know more about another person" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"to know more about another person\" could be:\n Janiya meets Weldon's girlfriend, Sasha, ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being a reformed smoker" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being a reformed smoker\" could be:\n Derrik was a heavy smoker for many years, but she finally gav...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Sincere: I'm really struggling with writer's block. I've been stuck on this book for months now and I just can't seem to get past it.\n Editor: That's definitely a tough situation to be in. I'm sure a lot of people c...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being a nice guy" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being a nice guy\" could be:\n Daylen is a nice guy who always brings coffee for Chaney. On Monday, Daylen...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Rosalie: Hey boss, I wanted to talk to you about something.\n Boss: What's up?\n Rosalie: I saw the job posting for the position I've always wanted and I wanted to apply for it. But before I do, I just wanted to get...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog about: Nicola meets his son because Nicola wants to be a good father" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Nicola meets his son because Nicola wants to be a good father\" could be:\n Nicola wanted...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n Cedar had a lot of money. Cedar came back with even more money. She now had a million dollars." }, { "from": "gpt", "value": "Sure, a dialog for this story could be:\n Cedar: Wow, I can't believe I now have a mill...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you give me a short story description for this dialog?\n Leeanna: I had a feeling something was going to happen.\n Stranger: What do you mean?\n Leeanna: I don't know. I just have a sense that something is about to happen, and I don't know what it is.\n Stranger: Do you ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being friendly" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being friendly\" could be:\n Oliva and Landree met for lunch. They discussed their shared interests and got ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Kahari: Thanks, coach. I've been working hard.\n Coach: It shows. You're one of the best players on the team.\n Kahari: Thank you, coach. I appreciate that.\n Coach: I'm not the only one who's noticed. I've been ge...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being emotional" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being emotional\" could be:\n Tears welled up in Armonie's eyes and spilled over, running down his cheeks. ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being controlling" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being controlling\" could be:\n Marisol controls every aspect of his girlfriend's life. He tells her what...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n Braydan put her coffee mug on the wrong shelf and it shattered. She wants to do it again because she's curious about what will happen." }, { "from": "gpt", "value": "Sure, a dialog for this story could be:\n Brayd...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n Montserrat is a very assertive person. He always tells the boss what he thinks and is never afraid to speak his mind. This can sometimes get him into trouble, but Montserrat always stands up for himself and his beliefs." }, ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being responsible" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being responsible\" could be:\n Edward is responsible for finding the doctor. She looks online and finds ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Keyonna: Hi Sarah! It's so nice to finally talk to you outside of school.\n Sarah: Hey Keyonna! Yeah, I've been meaning to call you for a while now." }, { "from": "gpt", "value": "Sure, the next dialog fo...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n \"I'm sorry, I just don't really think this is my thing,\" Kinsey replied. \"I'd rather go do something else.\"" }, { "from": "gpt", "value": "Sure, a dialog for this story could be:\n Kinsey: I'm sorry, I just do...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being outgoing" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being outgoing\" could be:\n Sahara is an outgoing student who loves meeting new people. When a new student,...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Millicent: Hey, I saw this movie yesterday that's been bothering me." }, { "from": "gpt", "value": "Sure, the next dialog for this scene could be:\n Girlfriend: What was it about?\n Millicent: It was abo...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being brave" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being brave\" could be:\n Bridger is a brave girl. She overcomes difficulties by facing them head on. She is ne...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Isreal: Hi, Daddy!" }, { "from": "gpt", "value": "Sure, the next dialog for this scene could be:\n Daddy: Hey there, kiddo! How was your day today?\n Isreal: It was good! I played with my friends at rece...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog about: Teague is perfectly polite" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Teague is perfectly polite\" could be:\n Teague is a very polite student. She always uses please and thank you when she spea...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:" }, { "from": "gpt", "value": "Sure, the next dialog for this scene could be:\n Dottie: I can't believe this is happening. I'm so scared.\n Alex: Try to stay calm, Dottie. We'll get through this together. J...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you give me a short story description for this dialog?\n Karma: Hey, boss. What's up?\n Boss: Not much. Just wanted to let you know that you're doing a great job as head teller.\n Karma: Thanks. I really appreciate it.\n Boss: You're welcome. I've been thinking about exp...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being excited" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being excited\" could be:\n Amada books a flight to Maui. He packed his swimsuit, sunscreen, and flip-flops i...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Lucianna: Hey girl, what's up?" }, { "from": "gpt", "value": "Sure, the next dialog for this scene could be:\n Best friend: Not much, just getting ready for my day. You?\n Lucianna: Oh, you know, just th...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Aleigha: Hey, Mom. I missed you.\n Mom: I missed you too, baby. I'm sorry I was gone for so long.\n Aleigha: It's okay. I'm just glad you're home now.\n Mom: Me too, sweetie. I love you so much.\n Aleigha: I love ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being safe" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being safe\" could be:\n Chandler was very afraid of the water, but she decided to get into a small boat. She fe...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog about: Briseyda buys grocery at Safeway" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Briseyda buys grocery at Safeway\" could be:\n Briseyda went to Safeway and bought some groceries. She got some fruits...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog about: Marah doesn't leave messages on the answering machine because Marah wants to avoid distractions" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Marah doesn't leave messages on the answering machine be...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n Jaleigh had been waiting at the park for Halli for half an hour when she finally arrived. He was angry at first, but he forgave her when she explained that she had gotten held up at work." }, { "from": "gpt", "valu...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Kirby: Hey Raj, it's so great to finally meet you in person! I feel like we've already bonded so much over our shared love of animals.\n Raj: I know, right? It's been really great getting to know you, Kirby. You're s...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being dependable" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being dependable\" could be:\n When the delivery truck arrived, Vaida was there to help unload it. They wo...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog about: Nash sings a song on Mazikeen's invitation because Nash wants to be a good friend" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Nash sings a song on Mazikeen's invitation because Nash wants to be a ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n to be free of the medication" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"to be free of the medication\" could be:\n Jazzmin was tired of feeling like a zombie and deci...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n Taryn doesn't want to hear what Simona has to say because Taryn is convinced that he is right and Simona is wrong. Taryn doesn't want to listen to Simona's side of the story because he knows that he is right and Simona is wron...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:" }, { "from": "gpt", "value": "Sure, the next dialog for this scene could be:\n Adrean: Hey, I'm Adrean. What's your name?\n Person: I'm Sarah. Nice to meet you, Adrean.\n Adrean: Likewise. So, what do you...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you give me a short story description for this dialog?\n Tamera: Hey, I heard that you've been seeing another woman on the side. Is that true?\n Zana: What? No, of course not. Who told you that?\n Tamera: Well, I don't want to say who, but someone saw you with her and the...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Sloane: You sure you want to do this? It's a lot of work.\n Dylen: Yes, I'm sure. I really want my project to be successful." }, { "from": "gpt", "value": "Sure, the next dialog for this scene could be:\n...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being doesn’t speak to another person" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being doesn’t speak to another person\" could be:\n Sanaa found that Rilynn was alway...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Alan: I don't understand. What's wrong with my novel?\n Editor: Well, there are a lot of typos and errors throughout the book.\n Alan: But I proofread it before I sent it to you!\n Editor: Apparently not carefully ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write a short dialog based on this story:\n Francisco resents being interrupted while she is trying to concentrate on her work. She feels irritated when her co-worker, Ken, starts talking to her about his weekend plans." }, { "from": "gpt", "value": "Sure, a...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Roxana: I'm sorry for breaking the alarm.\n Parent: We've told you time and time again not to play near the alarm. Now it's broken and we have to replace it.\n Roxana: I know, I'm sorry. I'll be more careful next ti...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being lazy" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being lazy\" could be:\n Brittani is too lazy to work. He would rather sit around all day and do nothing. Britta...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being open-minded" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being open-minded\" could be:\n Jamey and Brooklyne discuss their differing opinions on whether extraterr...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n wanting to do something good" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"wanting to do something good\" could be:\n Braedan realized that he had been selfish and decid...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being loved by another person's family" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being loved by another person's family\" could be:\n Kally lives in Trenity's house ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you give me a short story description for this dialog?\n Andrei: Mom, can we go to the park please? I really want to go!\n Andrei's mom: No, Andrei, we can't go to the park right now. Maybe another time.\n Andrei: But why?! I don't understand why we can't go! Please, Mom,...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being gets more coffee" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being gets more coffee\" could be:\n After Cain drinks his coffee, he realizes he wants more. He get...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being another person to be happy" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being another person to be happy\" could be:\n Denzell told Meera to think positively beca...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:" }, { "from": "gpt", "value": "Sure, the next dialog for this scene could be:\n Unknown: Hey Kaneisha, what's up?\n Kaneisha: Not much, just chilling. What about you?\n Unknown: I'm good. I've been thinkin...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Keshav: Hi, I'm Keshav. I got a letter from the bank saying that my account is overdrawn and I need to pay back the money soon. Is there anything you can do to help me?" }, { "from": "gpt", "value": "Sure,...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n to talk about her grandmother" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"to talk about her grandmother\" could be:\n Grandma was always supportive, whether I wanted t...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you give me a short story description for this dialog?\n Brion: Hey, what's up? You seem angry.\n Sammie: What do you care? You're always causing trouble. I don't want to be around you anymore.\n Brion: What are you talking about? I don't cause trouble, I just like to hav...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being immature" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being immature\" could be:\n Jacy is often late for appointments and forgets to return phone calls. When con...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being trustworthy" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being trustworthy\" could be:\n Aaliah tells Breonna that she saw her take a pen from Sarah's backpack.\n...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Bryanne: Hey boss, I was just taking a look at the new computer system. It looks really interesting. I'm eager to learn how to use it and get started with my work.\n Boss: Yeah, it's a great system. We just installed...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being sees a beautiful sunset" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being sees a beautiful sunset\" could be:\n Anisha is walking down the beach and admiring the...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog about: Keandra is rebellious" }, { "from": "gpt", "value": "Sure, a short story and dialog about: \"Keandra is rebellious\" could be:\n Keandra is a rebellious teenager who wants to change her town. She hates the small-mindedness...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being fired" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being fired\" could be:\n Rance was not up to the job. She was constantly making mistakes and her work was subp...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Kirah: Hi Emily. It's nice to meet you.\n Emily: Hi Kirah. Thanks for talking to me.\n Kirah: No problem, Emily. I'm just sorry that your mom and I are going through this right now." }, { "from": "gpt", ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Arika: Hey there! I'm Arika. What's your name?\n Person: I'm John. Nice to meet you, Arika. Where are you headed?\n Arika: I'm headed to Chicago for a business trip. I'm going to be there for a week.\n Person: That...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being productive" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being productive\" could be:\n Sherman patched a hole in the fence with some wood he found lying around. H...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being generous" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being generous\" could be:\n After Trevion gave Amie a large sum of money, Amie felt the urge to give back. ...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n being makes new friends" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"being makes new friends\" could be:\n Shea attends her high school reunion. She talks to old friend...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write the next few lines of dialog for this scene:\n Arion: Sarah, don't you just love the way the leaves fall from the tree? They're so graceful and peaceful.\n Sarah: Yes, I do. It's always been one of my favorite things to watch. There's something about the simplici...	processed_unified_soda_dialog	chosen
[ { "from": "human", "value": "Can you write short story and dialog based on the theme:\n to manage his money" }, { "from": "gpt", "value": "Sure, a short story and dialog based on the theme \"to manage his money\" could be:\n Francisco manages his own finances because he wants to be in control ...	processed_unified_soda_dialog	chosen

End of preview. Expand in Data Studio

Buzz: Advancing Efficiency through Iterative Fine-Tuning

Introduction

Alignment Lab AI is pleased to introduce our latest research efforts with:

Buzz, a highly curated pretraining scale assistant dataset, unifying RL and SFT, developed in collaboration with Hive Digital Technologies.

The Buzz model, Dataset, and Code are to be released to build a toolkit that aims to demonstrate the potential for reuse and optimization of existing pretrained language models to continuously refine the heights of performance that can be achieved with optimal use of FlOps. Alongside Buzz-8b-Large, we release

Features

Buzz contains 435 high quality instruction following and conversational datasets, deduplicated, with formatting built to maintain and extend compatibility between training types and the current local ecosystem.

the datasets within are comprised of various high quality instruction following, conversational, storytelling, and coding datasets, as well as over 5 million new rows of data, in addition to several million reaugmented rows of data, comprising the totality of the learned techniques since our release of Open-Orca cumulatively making up roughly 85 million turns of conversations, in a mix of single and multiturn rows.

Iterative Fine-Tuning Methodology

Our research builds upon the concepts introduced in several key papers, including:

By combining high quality data, iterative fine-tuning with carefully selected "grounding" distributions from previous epochs, we have developed a cost-effective approach that pushes the boundaries of model reuse and optimization.

notably, we observe that training on a single epoch of high quality in domain data can still achieve remarkably low loss values before overfitting.

Data structure and formatting

buzz should be out of the box compatible with the sharegpt type in Axolotl and lmsys' FastChat during training it containsthe following structure [EDIT]: filtered for bias examples!

{
  "source": "string containing the source dataset",
  "stack": "chosen/rejected for RL techniques",
  "question_index": optional row, only contained in DPO specific dataset to match dpo pairs - int64
  "conversations": [
    {
      "from": "system",
      "value": "an initial system prompt or user query, may or may not be present depending on the row"
    },
    {
      "from": "human or system",
      "value": "an initial 'human' query"
    },
    {
      "from": "gpt",
      "value": "a response to the previous turn, may be followed by additional human/gpt alternations"
    }
  ]
}

Conclusion

We intend to focus on updating and improving the dataset, tools to construct it, and other surrounding open sourced infrastructure. Our next effort will focus on context and implementing the research currently being conducted by Wing-Lian, the lead developer of the Axolotl training framework that underpins these experiments. We encourage the community to explore Wing-Lian's work, such as the Llama-3-8b-64k-PoSE and llama-3-8b-256k-PoSE models, which showcase the potential for further advancements in language modeling.

Buzz hopes to be a proof of concept, and a toolkit to demonstrate and enable the community in the pursuit of efficient and effective locally run, personally owned, language models. Through collaboration with Hive Digital Technologies who have enabled us to perform this research, we have demonstrated the immense potential for model reuse and optimization. The Buzz models and dataset are open sourced with [////////].

Credits

to the many researchers who have open sourced their knowledge and tools to allow us to pursue this,

to Hive Digital Technologies for providing compute, advice, and meaningful research insight.

to Meta for developing the Llama models, and maintaining a philosophy of supporting open research and open source.

To wing et al. with Open Access AI Collective for developing axolotl, assisting with research, and generally being geniuses.

to Thomas Capelle et al. working on LLM_Surgery

as well as many, many others who are too numerous to name.

Dataset Sources

Sources in the source column which refer only to a model name are from Nectar, Lmsys 55k preference, and various user submitted distillation datasets inspired by Ontocord's dataset https://huggingface.co/datasets/laion/OIG


Muennighoff/tasky-commits
Muennighoff/natural-instructions
laion/OIG
knowrohit07/know_medical_dialogue_v2
knowrohit07/know-saraswati-cot
knowrohit07/know_medical_dialogues
H-D-T/Select-Stack [stackexchange dump, filtered for difficult, stem, technical stacks, only best rated responses kept for Buzz]
knowrohit07/know_sql
knowrohit07/ArithmeLogic
knowrohit07/know_logic
knowrohit07/know_cot
knowrohit07/GPTscience_maths_csml
AlignmentLab-AI/datasci-python
teknium/OpenHermes-2.5
teknium/openhermes
THUDM/AgentInstruct
Vezora/Tested-22k-Python-Alpaca
HuggingFaceH4/no_robots
migtissera/Synthia-v1.3
migtissera/Tess-Coder-v1.0
migtissera/Quanta
AlekseyKorshuk/gpteacher-role-play-chatml
nampdn-ai/devdocs.io
TIGER-Lab/MathInstruct
TIGER-Lab/Homework-step-Comparator
TIGER-Lab/Homework-step-Extractor
TIGER-Lab/MATH-plus
TIGER-Lab/MetricInstruct
TIGER-Lab/RFT-GSM-28K
Muennighoff/P3
PygmalionAI/Sharegpt-soda
taesiri/arxiv_summary
kaist-ai/Cot-Collection
microsoft/orca-math-word-problems-200k
Open-Orca/FLAN [uploaded to hf, but created by Google]
allenai/WildChat
chargoddard/rpguild
medalpaca/medical_meadow_medqa
medalpaca/medical_meadow_mediqa
medalpaca/medical_meadow_wikidoc
medalpaca/medical_meadow_health_advice
medalpaca/medical_meadow_medical_flashcards
medalpaca/medical_meadow_cord19
medalpaca/medical_meadow_wikidoc_patient_information
medalpaca/medical_meadow_mmmlu
medalpaca/medical_meadow_pubmed_causal
medalpaca/medical_meadow_usmle_self_assessment
keivalya/MedQuad-MedicalQnADataset
IndianaUniversityDatasetsModels/MIMIC-medical-report
Annielytics/DoctorsNotes
lavita/ChatDoctor-HealthCareMagic-100k
lavita/ChatDoctor-iCliniq
mahfoos/Patient-Doctor-Conversation
Amod/mental_health_counseling_conversations
alexandreteles/mental-health-conversational-data
heliosbrahma/mental_health_chatbot_dataset
akemiH/NoteChat
openchat/cogstack-opengpt-sharegpt
h2oai/openassistant_oasst1_h2ogpt_llama2_chat
openchat/openchat_sharegpt4_dataset
garage-bAInd/Open-Platypus
lmsys/lmsys-arena-human-preference-55k
CarperAI/openai_summarize_tldr
Locutusque/OpenCerebrum-dpo
Locutusque/OpenCerebrum-2.0-SFT
internlm/Agent-FLAN
Clinton/Text-to-sql-v1
meta-math/MetaMath_DPO_FewShot
berkeley-nest/Nectar
bigcode/commitpackft
ybisk/piqa
meta-math/MetaMathQA
SAGI-1/reasoningData_200k

Total Turns: 81,167,793
Total Rows: 31,249,070

| # | Source | Percentage | Turns | Rows |
| - | ------ | ---------- | ----- | ---- |
| 1 | Flan: English | 20.33% | 16,500,966 | 8,250,483 |
| 2 | Flan: Non English | 18.47% | 14,995,714 | 7,497,857 |
| 3 | sodey | 9.71% | 7,883,090 | 917,016 |
| 4 | OIG soda_dialog | 7.93% | 6,436,873 | 1,191,582 |
| 5 | various 'orca' style reaugmentations | 3.62% | 2,934,794 | 878,547 |
| 6 | Select Stack | 3.59% | 2,911,650 | 1,455,825 |
| 7 | sft-distil | 3.59% | 2,911,634 | 1,455,817 |
| 8 | OIG abstract_infill | 3.52% | 2,858,795 | 232,188 |
| 9 | medical_meadow_cord19 | 2.79% | 2,265,654 | 755,218 |
| 10 | EverythingIsAllYouNeed0.25 | 2.39% | 1,941,198 | 970,599 |
| 11 | MATH-plus | 2.04% | 1,658,976 | 829,488 |
| 12 | OIG unifiedskg_instructions | 1.14% | 927,267 | 214,793 |
| 13 | OIG nq | 1.03% | 836,194 | 307,373 |
| 14 | MetaMath_DPO_FewShot | 0.97% | 787,998 | 393,999 |
| 15 | MetaMathQA | 0.95% | 770,166 | 385,083 |
| 16 | OpenHermes-2.5 | 0.95% | 769,503 | 367,336 |
| 17 | wildchat-sharegpt | 0.94% | 764,896 | 123,596 |
| 18 | hotdog-gpt | 0.73% | 591,467 | 190,543 |
| 19 | Tess-Coder-v1.0 | 0.72% | 585,038 | 117,008 |
| 20 | OIG canadian_parliament | 0.72% | 581,708 | 290,854 |
| 21 | openhermes | 0.66% | 536,782 | 240,894 |
| 22 | Text-to-sql-v1 | 0.65% | 524,412 | 262,206 |
| 23 | MathInstruct | 0.61% | 491,666 | 245,833 |
| 24 | OIG unnatural_instructions | 0.59% | 476,087 | 238,035 |
| 25 | OIG openai_summarize_tldr | 0.58% | 466,796 | 233,398 |
| 26 | OIG chip2 | 0.52% | 420,564 | 210,282 |
| 27 | orcamath-sharegpt | 0.49% | 399,414 | 199,707 |
| 28 | OIG xp3_sample | 0.46% | 376,276 | 188,138 |
| 29 | anthropic-hh-nectar | 0.43% | 346,892 | 73,687 |
| 30 | reasoningData_200k | 0.41% | 334,004 | 167,002 |
| 31 | OpenCodeInterpreterData | 0.41% | 331,715 | 36,836 |
| 32 | Synthia-v1.3 | 0.41% | 329,115 | 118,841 |
| 33 | yaml | 0.40% | 321,755 | 110,572 |
| 34 | GPTscience_maths_csml | 0.37% | 297,310 | 148,655 |
| 35 | OIG squad_v2 | 0.32% | 260,638 | 19,585 |
| 36 | OIG squad_v2_more_neg | 0.32% | 259,902 | 13,946 |
| 37 | OIG rallio_safety_and_prosocial | 0.31% | 250,534 | 125,235 |
| 38 | MIMIC-medical-report | 0.31% | 250,362 | 83,454 |
| 39 | OIG mathqa_flanv2_kojma_cot | 0.30% | 243,420 | 107,564 |
| 40 | openai_summarize_tldr | 0.29% | 233,336 | 116,668 |
| 41 | OIG sqlv2 | 0.28% | 224,270 | 24,546 |
| 42 | ruby | 0.24% | 197,135 | 68,086 |
| 43 | RPGuild-sharegpt-filtered | 0.24% | 196,309 | 27,053 |
| 44 | OIG multi_news | 0.22% | 179,888 | 89,944 |
| 45 | markdown | 0.22% | 174,608 | 61,260 |
| 46 | javascript | 0.19% | 156,109 | 52,289 |
| 47 | python | 0.19% | 151,866 | 55,045 |
| 48 | know_sql | 0.18% | 148,368 | 49,456 |
| 49 | text | 0.16% | 133,033 | 44,926 |
| 50 | saraswati_stem_formatted | 0.15% | 119,750 | 59,875 |
| 51 | know_saraswati_cot_formatted | 0.14% | 116,408 | 58,204 |
| 52 | json | 0.14% | 115,682 | 39,124 |
| 53 | OIG hc3_human | 0.14% | 112,112 | 56,056 |
| 54 | medical_meadow_medical_flashcards | 0.12% | 100,575 | 33,527 |
| 55 | lmsys-chat-1m-nectar | 0.11% | 86,770 | 43,385 |
| 56 | shell | 0.11% | 85,901 | 30,327 |
| 57 | cogstack-opengpt-sharegpt | 0.10% | 81,667 | 31,532 |
| 58 | Quanta | 0.10% | 78,096 | 26,032 |
| 59 | php | 0.08% | 68,256 | 24,302 |
| 60 | know_logic | 0.08% | 68,208 | 34,104 |
| 61 | html | 0.07% | 57,384 | 19,750 |
| 62 | OIG plot_screenplay_books_dialog | 0.07% | 54,981 | 7,924 |
| 63 | java | 0.07% | 53,574 | 20,150 |
| 64 | Open-Platypus | 0.07% | 53,373 | 24,109 |
| 65 | RFT-GSM-28K | 0.06% | 51,092 | 25,546 |
| 66 | OIG conv_finqa | 0.06% | 50,472 | 9,102 |
| 67 | sharegpt-nectar | 0.06% | 49,896 | 24,948 |
| 68 | OIG cuad | 0.05% | 41,390 | 510 |
| 69 | OpenCerebrum-dpo | 0.05% | 40,534 | 17,013 |
| 70 | Tested-22k-Python-Alpaca | 0.04% | 36,224 | 18,112 |
| 71 | OIG sqlv1 | 0.04% | 34,174 | 17,087 |
| 72 | MedQuad-MedicalQnADataset | 0.04% | 32,718 | 16,359 |
| 73 | piqa | 0.04% | 32,212 | 16,106 |
| 74 | html+erb | 0.04% | 31,679 | 10,708 |
| 75 | OIG image_prompts_instructions | 0.04% | 30,932 | 15,466 |
| 76 | medical_meadow_medqa | 0.04% | 30,534 | 10,178 |
| 77 | ini | 0.04% | 30,461 | 10,396 |
| 78 | medical_meadow_wikidoc | 0.04% | 29,998 | 10,000 |
| 79 | c# | 0.03% | 26,796 | 9,220 |
| 80 | xml | 0.03% | 26,054 | 9,085 |
| 81 | medical_meadow_health_advice | 0.03% | 25,995 | 8,665 |
| 82 | OIG poetry_2_song | 0.03% | 25,462 | 12,731 |
| 83 | flan_v2_niv2-nectar | 0.03% | 24,036 | 12,018 |
| 84 | c | 0.03% | 23,203 | 8,250 |
| 85 | scss | 0.02% | 20,156 | 6,730 |
| 86 | evol_instruct-nectar | 0.02% | 19,930 | 9,965 |
| 87 | ultrachat-nectar | 0.02% | 19,822 | 9,911 |
| 88 | restructuredtext | 0.02% | 18,901 | 6,481 |
| 89 | OpenCerebrum-2.0-SFT | 0.02% | 18,793 | 4,382 |
| 90 | gpteacher-role-play-chatml | 0.02% | 18,222 | 9,111 |
| 91 | OIG grade_school_math_instructions | 0.02% | 17,584 | 8,792 |
| 92 | OIG essays | 0.02% | 17,581 | 2,064 |
| 93 | medical_meadow_wikidoc_patient_information | 0.02% | 17,550 | 5,850 |
| 94 | typescript | 0.02% | 16,912 | 5,816 |
| 95 | coffeescript | 0.02% | 15,836 | 5,403 |
| 96 | go | 0.02% | 14,814 | 4,939 |
| 97 | css | 0.02% | 14,654 | 4,979 |
| 98 | scala | 0.02% | 14,184 | 4,988 |
| 99 | c++ | 0.02% | 13,391 | 4,838 |
| 100 | swift | 0.02% | 13,361 | 4,724 |
| 101 | haml | 0.02% | 12,787 | 4,285 |
| 102 | know_medical_dialogue_v2 | 0.02% | 12,580 | 6,290 |
| 103 | medical_meadow_mmmlu | 0.01% | 11,058 | 3,686 |
| 104 | toml | 0.01% | 10,189 | 3,411 |
| 105 | riddler_formatted | 0.01% | 8,396 | 4,198 |
| 106 | rust | 0.01% | 8,276 | 2,977 |
| 107 | gpt-4-1106-preview | 0.01% | 8,106 | 4,053 |
| 108 | extractor-00000-of-00001 | 0.01% | 7,678 | 3,839 |
| 109 | clojure | 0.01% | 6,974 | 2,394 |
| 110 | Patient-Doctor-Conversation | 0.01% | 6,488 | 3,244 |
| 111 | jsx | 0.01% | 6,390 | 2,176 |
| 112 | kotlin | 0.01% | 6,206 | 2,193 |
| 113 | medical_meadow_mediqa | 0.01% | 6,162 | 2,054 |
| 114 | flan_v2_cot-nectar | 0.01% | 6,000 | 3,000 |
| 115 | perl | 0.01% | 5,837 | 2,217 |
| 116 | mental_health_counseling_conversations | 0.01% | 5,496 | 2,748 |
| 117 | sql | 0.01% | 5,172 | 1,998 |
| 118 | gpt-4-0613 | 0.01% | 4,862 | 2,431 |
| 119 | gpt-3.5-turbo-0613 | 0.01% | 4,742 | 2,371 |
| 120 | nix | 0.01% | 4,704 | 1,582 |
| 121 | false_qa-nectar | 0.01% | 4,640 | 2,320 |
| 122 | unknown | 0.01% | 4,576 | 1,571 |
| 123 | twig | 0.01% | 4,557 | 1,563 |
| 124 | handlebars | 0.01% | 4,176 | 1,405 |
| 125 | haskell | 0.01% | 4,095 | 1,365 |
| 126 | batchfile | 0.00% | 4,003 | 1,409 |
| 127 | less | 0.00% | 3,973 | 1,331 |
| 128 | datasci-python | 0.00% | 3,966 | 1,983 |
| 129 | gpt-4-0314 | 0.00% | 3,962 | 1,981 |
| 130 | groovy | 0.00% | 3,952 | 1,470 |
| 131 | flan_v2_p3-nectar | 0.00% | 3,858 | 1,929 |
| 132 | OIG poetry_instructions | 0.00% | 3,508 | 1,754 |
| 133 | claude-1 | 0.00% | 3,476 | 1,738 |
| 134 | bitbake | 0.00% | 3,419 | 1,264 |
| 135 | claude-2.1 | 0.00% | 3,400 | 1,700 |
| 136 | jade | 0.00% | 3,282 | 1,101 |
| 137 | elixir | 0.00% | 3,281 | 1,138 |
| 138 | claude-instant-1 | 0.00% | 3,262 | 1,631 |
| 139 | viml | 0.00% | 3,150 | 1,050 |
| 140 | slim | 0.00% | 3,111 | 1,043 |
| 141 | emacs-lisp | 0.00% | 2,884 | 983 |
| 142 | cmake | 0.00% | 2,876 | 959 |
| 143 | makefile | 0.00% | 2,721 | 933 |
| 144 | powershell | 0.00% | 2,690 | 970 |
| 145 | cucumber | 0.00% | 2,632 | 951 |
| 146 | llama-2-70b-chat | 0.00% | 2,546 | 1,273 |
| 147 | vicuna-33b | 0.00% | 2,526 | 1,263 |
| 148 | lua | 0.00% | 2,517 | 904 |
| 149 | vicuna-13b | 0.00% | 2,482 | 1,241 |
| 150 | mistral-medium | 0.00% | 2,438 | 1,219 |
| 151 | mixtral-8x7b-instruct-v0.1 | 0.00% | 2,390 | 1,195 |
| 152 | fish | 0.00% | 2,275 | 802 |
| 153 | common-lisp | 0.00% | 2,234 | 761 |
| 154 | smarty | 0.00% | 2,127 | 723 |
| 155 | dart | 0.00% | 2,092 | 750 |
| 156 | sass | 0.00% | 2,060 | 692 |
| 157 | llvm | 0.00% | 1,991 | 778 |
| 158 | claude-2.0 | 0.00% | 1,902 | 951 |
| 159 | saltstack | 0.00% | 1,818 | 617 |
| 160 | gpt-3.5-turbo-1106 | 0.00% | 1,724 | 862 |
| 161 | llama-2-13b-chat | 0.00% | 1,712 | 856 |
| 162 | vue | 0.00% | 1,705 | 583 |
| 163 | diff | 0.00% | 1,564 | 656 |
| 164 | asciidoc | 0.00% | 1,523 | 508 |
| 165 | truthful_qa-nectar | 0.00% | 1,488 | 744 |
| 166 | zephyr-7b-beta | 0.00% | 1,428 | 714 |
| 167 | gpt-3.5-turbo-0314 | 0.00% | 1,418 | 709 |
| 168 | stylus | 0.00% | 1,414 | 476 |
| 169 | freemarker | 0.00% | 1,322 | 508 |
| 170 | erlang | 0.00% | 1,286 | 468 |
| 171 | palm-2 | 0.00% | 1,270 | 635 |
| 172 | hcl | 0.00% | 1,206 | 420 |
| 173 | gpt-4-0125-preview | 0.00% | 1,192 | 596 |
| 174 | html+django | 0.00% | 1,174 | 394 |
| 175 | wizardlm-70b | 0.00% | 1,170 | 585 |
| 176 | wizardlm-13b | 0.00% | 1,140 | 570 |
| 177 | koala-13b | 0.00% | 1,120 | 560 |
| 178 | llama-2-7b-chat | 0.00% | 1,106 | 553 |
| 179 | yi-34b-chat | 0.00% | 1,062 | 531 |
| 180 | qml | 0.00% | 1,053 | 362 |
| 181 | csv | 0.00% | 1,010 | 368 |
| 182 | gemini-pro-dev-api | 0.00% | 954 | 477 |
| 183 | know_medical_dialogues | 0.00% | 952 | 476 |
| 184 | openchat-3.5 | 0.00% | 944 | 472 |
| 185 | flan_v2_flan2021-nectar | 0.00% | 928 | 464 |
| 186 | ocaml | 0.00% | 912 | 327 |
| 187 | gemini-pro | 0.00% | 906 | 453 |
| 188 | pplx-70b-online | 0.00% | 896 | 448 |
| 189 | vicuna-7b | 0.00% | 894 | 447 |
| 190 | codellama-34b-instruct | 0.00% | 852 | 426 |
| 191 | tex | 0.00% | 839 | 297 |
| 192 | starling-lm-7b-alpha | 0.00% | 800 | 400 |
| 193 | rdoc | 0.00% | 795 | 269 |
| 194 | mistral-7b-instruct | 0.00% | 774 | 387 |
| 195 | elm | 0.00% | 772 | 265 |
| 196 | tulu-2-dpo-70b | 0.00% | 756 | 378 |
| 197 | f# | 0.00% | 743 | 251 |
| 198 | alpaca-13b | 0.00% | 710 | 355 |
| 199 | smalltalk | 0.00% | 706 | 284 |
| 200 | oasst-pythia-12b | 0.00% | 684 | 342 |
| 201 | pplx-7b-online | 0.00% | 656 | 328 |
| 202 | ada | 0.00% | 650 | 261 |
| 203 | scheme | 0.00% | 598 | 212 |
| 204 | openhermes-2.5-mistral-7b | 0.00% | 560 | 280 |
| 205 | qwen-14b-chat | 0.00% | 550 | 275 |
| 206 | arduino | 0.00% | 544 | 224 |
| 207 | crystal | 0.00% | 536 | 182 |
| 208 | RWKV-4-Raven-14B | 0.00% | 530 | 265 |
| 209 | gpt-3.5-turbo-0125 | 0.00% | 528 | 264 |
| 210 | gas | 0.00% | 502 | 192 |
| 211 | desktop | 0.00% | 500 | 174 |
| 212 | protocol-buffer | 0.00% | 500 | 180 |
| 213 | julia | 0.00% | 494 | 180 |
| 214 | guanaco-33b | 0.00% | 492 | 246 |
| 215 | haxe | 0.00% | 488 | 173 |
| 216 | groff | 0.00% | 485 | 188 |
| 217 | solar-10.7b-instruct-v1.0 | 0.00% | 484 | 242 |
| 218 | mako | 0.00% | 480 | 166 |
| 219 | glsl | 0.00% | 471 | 157 |
| 220 | java-server-pages | 0.00% | 463 | 163 |
| 221 | chatglm-6b | 0.00% | 432 | 216 |
| 222 | html+php | 0.00% | 432 | 146 |
| 223 | qwen1.5-72b-chat | 0.00% | 426 | 213 |
| 224 | mpt-7b-chat | 0.00% | 426 | 213 |
| 225 | svg | 0.00% | 425 | 166 |
| 226 | mpt-30b-chat | 0.00% | 414 | 207 |
| 227 | stripedhyena-nous-7b | 0.00% | 412 | 206 |
| 228 | html+eex | 0.00% | 405 | 135 |
| 229 | openassistant_oasst1_h2ogpt_llama2_chat | 0.00% | 404 | 202 |
| 230 | qmake | 0.00% | 401 | 135 |
| 231 | fastchat-t5-3b | 0.00% | 388 | 194 |
| 232 | org | 0.00% | 383 | 136 |
| 233 | deepseek-llm-67b-chat | 0.00% | 378 | 189 |
| 234 | llama2-70b-steerlm-chat | 0.00% | 358 | 179 |
| 235 | rhtml | 0.00% | 356 | 124 |
| 236 | cython | 0.00% | 322 | 115 |
| 237 | racket | 0.00% | 321 | 116 |
| 238 | perl6 | 0.00% | 317 | 116 |
| 239 | chatglm3-6b | 0.00% | 314 | 157 |
| 240 | r | 0.00% | 312 | 119 |
| 241 | factor | 0.00% | 287 | 99 |
| 242 | unity3d-asset | 0.00% | 282 | 101 |
| 243 | m4 | 0.00% | 279 | 99 |
| 244 | tcl | 0.00% | 267 | 98 |
| 245 | stablelm-tuned-alpha-7b | 0.00% | 264 | 132 |
| 246 | assembly | 0.00% | 260 | 104 |
| 247 | xslt | 0.00% | 251 | 96 |
| 248 | dolly-v2-12b | 0.00% | 248 | 124 |
| 249 | mind2web-00000-of-00001-fc25d47330eea0fc | 0.00% | 242 | 121 |
| 250 | objective-c++ | 0.00% | 238 | 84 |
| 251 | zephyr-7b-alpha | 0.00% | 236 | 118 |
| 252 | purescript | 0.00% | 225 | 80 |
| 253 | robotframework | 0.00% | 216 | 84 |
| 254 | nous-hermes-2-mixtral-8x7b-dpo | 0.00% | 212 | 106 |
| 255 | standard-ml | 0.00% | 192 | 71 |
| 256 | dolphin-2.2.1-mistral-7b | 0.00% | 190 | 95 |
| 257 | fortran | 0.00% | 187 | 70 |
| 258 | gpt4all-13b-snoozy | 0.00% | 186 | 93 |
| 259 | livescript | 0.00% | 178 | 62 |
| 260 | llama-13b | 0.00% | 176 | 88 |
| 261 | textile | 0.00% | 173 | 60 |
| 262 | nimrod | 0.00% | 173 | 66 |
| 263 | falcon-180b-chat | 0.00% | 156 | 78 |
| 264 | xtend | 0.00% | 155 | 55 |
| 265 | gettext-catalog | 0.00% | 147 | 65 |
| 266 | ceylon | 0.00% | 146 | 49 |
| 267 | chatglm2-6b | 0.00% | 146 | 73 |
| 268 | vala | 0.00% | 143 | 50 |
| 269 | edn | 0.00% | 138 | 47 |
| 270 | awk | 0.00% | 133 | 52 |
| 271 | actionscript | 0.00% | 132 | 48 |
| 272 | visual-basic | 0.00% | 131 | 47 |
| 273 | pod | 0.00% | 130 | 48 |
| 274 | sqf | 0.00% | 127 | 43 |
| 275 | openchat-3.5-0106 | 0.00% | 126 | 63 |
| 276 | dockerfile | 0.00% | 115 | 39 |
| 277 | linker-script | 0.00% | 108 | 36 |
| 278 | idris | 0.00% | 107 | 37 |
| 279 | qwen1.5-7b-chat | 0.00% | 102 | 51 |
| 280 | solidity | 0.00% | 102 | 36 |
| 281 | systemverilog | 0.00% | 101 | 35 |
| 282 | json5 | 0.00% | 98 | 33 |
| 283 | jupyter-notebook | 0.00% | 98 | 47 |
| 284 | processing | 0.00% | 96 | 35 |
| 285 | mediawiki | 0.00% | 94 | 33 |
| 286 | rouge | 0.00% | 92 | 41 |
| 287 | xquery | 0.00% | 89 | 38 |
| 288 | graphviz-dot | 0.00% | 84 | 32 |
| 289 | liquid | 0.00% | 83 | 29 |
| 290 | thrift | 0.00% | 77 | 28 |
| 291 | groovy-server-pages | 0.00% | 75 | 25 |
| 292 | pan | 0.00% | 69 | 23 |
| 293 | qwen1.5-4b-chat | 0.00% | 68 | 34 |
| 294 | api-blueprint | 0.00% | 67 | 23 |
| 295 | opencl | 0.00% | 66 | 23 |
| 296 | asp | 0.00% | 64 | 22 |
| 297 | cuda | 0.00% | 64 | 25 |
| 298 | logtalk | 0.00% | 63 | 21 |
| 299 | pascal | 0.00% | 62 | 24 |
| 300 | chapel | 0.00% | 60 | 20 |
| 301 | sparql | 0.00% | 60 | 23 |
| 302 | coldfusion-cfc | 0.00% | 58 | 20 |
| 303 | applescript | 0.00% | 57 | 19 |
| 304 | parrot-internal-representation | 0.00% | 56 | 20 |
| 305 | logos | 0.00% | 55 | 19 |
| 306 | mistral-7b-instruct-v0.2 | 0.00% | 54 | 27 |
| 307 | literate-coffeescript | 0.00% | 54 | 19 |
| 308 | digital-command-language | 0.00% | 53 | 19 |
| 309 | turtle | 0.00% | 52 | 21 |
| 310 | ioke | 0.00% | 52 | 19 |
| 311 | pony | 0.00% | 48 | 16 |
| 312 | openscad | 0.00% | 48 | 21 |
| 313 | vcl | 0.00% | 48 | 17 |
| 314 | graphql | 0.00% | 48 | 17 |
| 315 | dm | 0.00% | 46 | 16 |
| 316 | gnuplot | 0.00% | 45 | 17 |
| 317 | ooc | 0.00% | 43 | 15 |
| 318 | inno-setup | 0.00% | 43 | 15 |
| 319 | gentoo-ebuild | 0.00% | 42 | 15 |
| 320 | modelica | 0.00% | 42 | 15 |
| 321 | antlr | 0.00% | 42 | 15 |
| 322 | nsis | 0.00% | 41 | 15 |
| 323 | http | 0.00% | 38 | 18 |
| 324 | ninja | 0.00% | 36 | 14 |
| 325 | mirah | 0.00% | 36 | 15 |
| 326 | autohotkey | 0.00% | 36 | 15 |
| 327 | augeas | 0.00% | 35 | 13 |
| 328 | hy | 0.00% | 32 | 11 |
| 329 | hlsl | 0.00% | 32 | 11 |
| 330 | stata | 0.00% | 30 | 10 |
| 331 | piglatin | 0.00% | 30 | 11 |
| 332 | capn-proto | 0.00% | 28 | 10 |
| 333 | moonscript | 0.00% | 28 | 10 |
| 334 | coldfusion | 0.00% | 27 | 9 |
| 335 | volt | 0.00% | 27 | 9 |
| 336 | tcsh | 0.00% | 25 | 10 |
| 337 | jasmin | 0.00% | 25 | 9 |
| 338 | raml | 0.00% | 25 | 9 |
| 339 | postscript | 0.00% | 25 | 9 |
| 340 | scilab | 0.00% | 25 | 10 |
| 341 | fancy | 0.00% | 24 | 8 |
| 342 | gdscript | 0.00% | 24 | 8 |
| 343 | latte | 0.00% | 21 | 7 |
| 344 | aspectj | 0.00% | 20 | 7 |
| 345 | apl | 0.00% | 20 | 7 |
| 346 | xs | 0.00% | 20 | 7 |
| 347 | g-code | 0.00% | 19 | 7 |
| 348 | nesc | 0.00% | 19 | 7 |
| 349 | emberscript | 0.00% | 19 | 7 |
| 350 | ston | 0.00% | 18 | 6 |
| 351 | oz | 0.00% | 18 | 7 |
| 352 | literate-haskell | 0.00% | 18 | 7 |
| 353 | yang | 0.00% | 17 | 6 |
| 354 | webidl | 0.00% | 17 | 6 |
| 355 | jsonld | 0.00% | 16 | 6 |
| 356 | jsoniq | 0.00% | 16 | 6 |
| 357 | lfe | 0.00% | 16 | 6 |
| 358 | pike | 0.00% | 15 | 6 |
| 359 | purebasic | 0.00% | 15 | 5 |
| 360 | pov-ray-sdl | 0.00% | 14 | 5 |
| 361 | lilypond | 0.00% | 13 | 6 |
| 362 | agda | 0.00% | 13 | 5 |
| 363 | vhdl | 0.00% | 13 | 5 |
| 364 | zephir | 0.00% | 12 | 4 |
| 365 | mupad | 0.00% | 12 | 4 |
| 366 | mask | 0.00% | 12 | 4 |
| 367 | krl | 0.00% | 12 | 4 |
| 368 | zig | 0.00% | 12 | 4 |
| 369 | metal | 0.00% | 12 | 4 |
| 370 | slash | 0.00% | 12 | 4 |
| 371 | io | 0.00% | 12 | 4 |
| 372 | monkey | 0.00% | 12 | 4 |
| 373 | ragel-in-ruby-host | 0.00% | 10 | 4 |
| 374 | xbase | 0.00% | 9 | 3 |
| 375 | eagle | 0.00% | 9 | 4 |
| 376 | squirrel | 0.00% | 9 | 4 |
| 377 | genshi | 0.00% | 9 | 3 |
| 378 | cartocss | 0.00% | 9 | 3 |
| 379 | xproc | 0.00% | 9 | 3 |
| 380 | wisp | 0.00% | 9 | 3 |
| 381 | urweb | 0.00% | 9 | 3 |
| 382 | yacc | 0.00% | 8 | 3 |
| 383 | smt | 0.00% | 8 | 3 |
| 384 | medical_meadow_pubmed_causal | 0.00% | 8 | 4 |
| 385 | lsl | 0.00% | 8 | 3 |
| 386 | ats | 0.00% | 8 | 3 |
| 387 | flux | 0.00% | 8 | 3 |
| 388 | bro | 0.00% | 8 | 3 |
| 389 | ecl | 0.00% | 8 | 4 |
| 390 | nit | 0.00% | 7 | 3 |
| 391 | pawn | 0.00% | 7 | 3 |
| 392 | rebol | 0.00% | 7 | 3 |
| 393 | mtml | 0.00% | 6 | 2 |
| 394 | eiffel | 0.00% | 6 | 2 |
| 395 | c2hs-haskell | 0.00% | 6 | 2 |
| 396 | uno | 0.00% | 6 | 2 |
| 397 | lean | 0.00% | 6 | 3 |
| 398 | sourcepawn | 0.00% | 6 | 3 |
| 399 | brainfuck | 0.00% | 6 | 2 |
| 400 | renpy | 0.00% | 6 | 2 |
| 401 | boo | 0.00% | 6 | 2 |
| 402 | arc | 0.00% | 6 | 2 |
| 403 | dylan | 0.00% | 6 | 2 |
| 404 | bluespec | 0.00% | 6 | 2 |
| 405 | creole | 0.00% | 6 | 2 |
| 406 | forth | 0.00% | 6 | 2 |
| 407 | apacheconf | 0.00% | 6 | 2 |
| 408 | isabelle | 0.00% | 5 | 2 |
| 409 | maple | 0.00% | 5 | 2 |
| 410 | dns-zone | 0.00% | 5 | 2 |
| 411 | nginx | 0.00% | 5 | 2 |
| 412 | inform-7 | 0.00% | 5 | 2 |
| 413 | csound | 0.00% | 4 | 2 |
| 414 | nu | 0.00% | 4 | 2 |
| 415 | supercollider | 0.00% | 4 | 2 |
| 416 | parrot-assembly | 0.00% | 3 | 1 |
| 417 | literate-agda | 0.00% | 3 | 1 |
| 418 | igor-pro | 0.00% | 3 | 1 |
| 419 | unrealscript | 0.00% | 3 | 1 |
| 420 | pure-data | 0.00% | 3 | 1 |
| 421 | blitzmax | 0.00% | 3 | 1 |
| 422 | sage | 0.00% | 3 | 1 |
| 423 | module-management-system | 0.00% | 3 | 1 |
| 424 | scaml | 0.00% | 3 | 1 |
| 425 | netlinx | 0.00% | 3 | 1 |
| 426 | abap | 0.00% | 3 | 1 |
| 427 | xpages | 0.00% | 3 | 1 |
| 428 | propeller-spin | 0.00% | 3 | 1 |
| 429 | sas | 0.00% | 3 | 1 |
| 430 | ArithmeLogic | 0.00% | 2 | 1 |
| 431 | clean | 0.00% | 2 | 1 |
| 432 | harbour | 0.00% | 2 | 1 |
| 433 | mathematica | 0.00% | 2 | 1 |
| 434 | jflex | 0.00% | 2 | 1 |
| 435 | red | 0.00% | 2 | 1 |

Citations

@misc{ibrahim2024simple,
      title={Simple and Scalable Strategies to Continually Pre-train Large Language Models}, 
      author={Adam Ibrahim and Benjamin Thérien and Kshitij Gupta and Mats L. Richter and Quentin Anthony and Timothée Lesort and Eugene Belilovsky and Irina Rish},
      year={2024},
      eprint={2403.08763},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@misc{jain2023neftune,
      title={NEFTune: Noisy Embeddings Improve Instruction Finetuning}, 
      author={Neel Jain and Ping-yeh Chiang and Yuxin Wen and John Kirchenbauer and Hong-Min Chu and Gowthami Somepalli and Brian R. Bartoldson and Bhavya Kailkhura and Avi Schwarzschild and Aniruddha Saha and Micah Goldblum and Jonas Geiping and Tom Goldstein},
      year={2023},
      eprint={2310.05914},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{wang2020optimistic,
      title={An Optimistic Acceleration of AMSGrad for Nonconvex Optimization}, 
      author={Jun-Kun Wang and Xiaoyun Li and Belhal Karimi and Ping Li},
      year={2020},
      eprint={1903.01435},
      archivePrefix={arXiv},
      primaryClass={stat.ML}
}

@misc{keskar2017improving,
      title={Improving Generalization Performance by Switching from Adam to SGD}, 
      author={Nitish Shirish Keskar and Richard Socher},
      year={2017},
      eprint={1712.07628},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@misc{mukherjee2023orca,
      title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, 
      author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
      year={2023},
      eprint={2306.02707},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 67

Size of the auto-converted Parquet files:

2.55 GB

Number of rows:

3,086,976

Papers for H-D-T/Buzz-slice-3-10-V1.2