Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

. Jonathan Whitaker 's talk: Napkin Math For Fine Tuning was so popular that we ended up doing an encore! He answers q's like: - When should I use LoRA? Quantization? GC? - What’s the cheapest option? most accurate? - What hardware? - What batch size / context length ..etc?

Hamel Husain

42,981 subscribers

109,951 views • 2 years ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Hamel Husain2 years ago

The talk is from

Vijayabhaskar J2 years ago

@johnowhitaker @johnowhitaker has one of the most underrated Youtube channels in ML.

Hamel Husain2 years ago

@johnowhitaker He is the most underrated person in ML. My goal is to make sure he is not underrated for too much longer 🥰

Krum Arnaudov2 years ago

@johnowhitaker @HamelHusain Do you plan to collect the parts of the talks that are intended to be openly shared somewhere? It is such a treasure trove.

Hamel Husain2 years ago

@johnowhitaker Right here, on twitter 😂

Leonard Tang2 years ago

@johnowhitaker ignore all advice and use reft @aryaman2020

eugene2 years ago

@eugeneyan @johnowhitaker shoot i had to miss this; wen encore?

Hamel Husain2 years ago

@eugeneyan @johnowhitaker It is in the recordings in maven

Xeophon2 years ago

@johnowhitaker Will this be uploaded somewhere else by any chance? Twitter video player is the worst :(

accelerate fit for purpose technology2 years ago

@johnowhitaker The visualization of the memory constraints, CPUs, GPUs relating to the size of models, gradients, etc. was fantastic. Made choices between tuning on full model, lorsa, qlora clear and obvious.

Related Videos

260404 new_ encore d1 ending ment #VERNON #버논 🐻‍❄️ when circles started, i was so surprised the view unfolded so beautifully that i ended up missing my part. my part “where am i headed? what am i searching for?” – it’s a thought i’ve often had throughout my time in seventeen. i’ve pondered about it many times. when there were many tough times, i thought “what’s there after this [difficult] process!” “what am i doing this for?” but i believe the people gathered in these seats have become the answer to that question. so i’d like to express my gratitude, and see you again. thank you.

260404 new_ encore d1 ending ment #VERNON #버논 🐻‍❄️ when circles started, i was so surprised the view unfolded so beautifully that i ended up missing my part. my part “where am i headed? what am i searching for?” – it’s a thought i’ve often had throughout my time in seventeen. i’ve pondered about it many times. when there were many tough times, i thought “what’s there after this [difficult] process!” “what am i doing this for?” but i believe the people gathered in these seats have become the answer to that question. so i’d like to express my gratitude, and see you again. thank you.

🎧

98,133 views • 4 months ago

hanbin was asked to compliment the members 🥹 🐹 as for taerae, he’s very cute nowadays! how should i put this... i can feel that he practices so much even when i’m not around to see it. isn’t it so admirable, how he does it both for himself and the team? 🐹 ah, have i said this before? when we were practicing for v for vision, i noticed something and thought about how i should mention it to him tomorrow. then the next day came, but when we actually did it, the thing i noticed was gone, so i was like huh... i asked him, “taerae-yah, when did you fix that?” and he told me, “i was monitoring it yesterday when i felt like i was doing it differently from the hyungs, so i fixed it!” so i was like, wow... what’s this!

hanbin was asked to compliment the members 🥹 🐹 as for taerae, he’s very cute nowadays! how should i put this... i can feel that he practices so much even when i’m not around to see it. isn’t it so admirable, how he does it both for himself and the team? 🐹 ah, have i said this before? when we were practicing for v for vision, i noticed something and thought about how i should mention it to him tomorrow. then the next day came, but when we actually did it, the thing i noticed was gone, so i was like huh... i asked him, “taerae-yah, when did you fix that?” and he told me, “i was monitoring it yesterday when i felt like i was doing it differently from the hyungs, so i fixed it!” so i was like, wow... what’s this!

지

76,261 views • 2 months ago

WOAH YoungK actually made around 25 tracks for YOUNGEST🤯 🦊the most YoungK-like, the most Kang Younghyun-like. with DAY6’s music and the band, i feel like i’ve done well with the missions that were given to me. so now i’m like, ‘what i actually want to do? what do i like? what am i best at?’ i didn’t know any of that, so this album was a process of finding it. that’s why i ended up making about 15 tracks all with different vibes, and then cut around 10 of them.

WOAH YoungK actually made around 25 tracks for YOUNGEST🤯 🦊the most YoungK-like, the most Kang Younghyun-like. with DAY6’s music and the band, i feel like i’ve done well with the missions that were given to me. so now i’m like, ‘what i actually want to do? what do i like? what am i best at?’ i didn’t know any of that, so this album was a process of finding it. that’s why i ended up making about 15 tracks all with different vibes, and then cut around 10 of them.

woodyꕤ 𝐘𝐎𝐔𝐍𝐆𝐄𝐒𝐓 🗝️🚪

16,565 views • 16 days ago

#เมาท์มอยกับพลอยหอxPhuwin #ปอนด์ภูวินทร์ Phu: If there numbers of works, we being together for almost 24hours MC: Yes Phu: And it will be like many others cp that been together for 7-8 yrs, or if we see our parents. Its just being together, but its not like... smtimes we might not talk to eo MC: Bc we met everyday Phu: Yes. So we don't know what to talk about MC: Its run out of topic Phu: Yes. If we meet friends, smtimes we are like "how are u these days? What are u doing last week" and etc. We don't hv that bc, yda I met u. Today I also met u. Tmr I will meet u again. I don't know what to talk bc I'm stay with u everyday MC: I'm run out of topic to talk with u Phu: Yes. There was 1 time he walked in "wassup" "ssup" then sat. And he was like ... want to talk. Both know that we want to talk but there is nothing to talk about bc yda I also met, already talked. Toady met too. So I don't know what to talk again MC: It like u already update

#เมาท์มอยกับพลอยหอxPhuwin #ปอนด์ภูวินทร์ Phu: If there numbers of works, we being together for almost 24hours MC: Yes Phu: And it will be like many others cp that been together for 7-8 yrs, or if we see our parents. Its just being together, but its not like... smtimes we might not talk to eo MC: Bc we met everyday Phu: Yes. So we don't know what to talk about MC: Its run out of topic Phu: Yes. If we meet friends, smtimes we are like "how are u these days? What are u doing last week" and etc. We don't hv that bc, yda I met u. Today I also met u. Tmr I will meet u again. I don't know what to talk bc I'm stay with u everyday MC: I'm run out of topic to talk with u Phu: Yes. There was 1 time he walked in "wassup" "ssup" then sat. And he was like ... want to talk. Both know that we want to talk but there is nothing to talk about bc yda I also met, already talked. Toady met too. So I don't know what to talk again MC: It like u already update

Az91saifar :)

50,331 views • 1 year ago

CNN’s Abby Phillip: “What kind of protest is OK with you?” Joe Borelli: “Parts that don't involve the impediment of law enforcement doing their constitutionally protected duty of enforcing the law.” Abby Phillip: “So what about filming an ICE officer?” Joe Borelli: “Filming an ICE officer is fine.” “Why are we talking about this?… [When] the incident that happened was a person that hit an officer with car.” “Attacks on ICE agents are up 3,600%… by vehicle[s].”

CNN’s Abby Phillip: “What kind of protest is OK with you?” Joe Borelli: “Parts that don't involve the impediment of law enforcement doing their constitutionally protected duty of enforcing the law.” Abby Phillip: “So what about filming an ICE officer?” Joe Borelli: “Filming an ICE officer is fine.” “Why are we talking about this?… [When] the incident that happened was a person that hit an officer with car.” “Attacks on ICE agents are up 3,600%… by vehicle[s].”

RedWave Press

364,398 views • 6 months ago

Jennings: In the case of Miles Taylor, was working in the government anonymously, obviously disseminating information publicly that he should not have been doing. Phillip: Like what? Jennings: Well, I mean, he was anonymously writing pieces for the New York Times and stating publicly that he was trying to undermine the government of the United States Philip: What did he disseminate that he was legally not allowed to do? Jennings: Great thing to find out Phillip: He wrote a book. What’s the allegation? There not allowed to talk about their experiences when they leave government? Jennigs: I’m saying he used his position to try to undermine the sitting president..

Jennings: In the case of Miles Taylor, was working in the government anonymously, obviously disseminating information publicly that he should not have been doing. Phillip: Like what? Jennings: Well, I mean, he was anonymously writing pieces for the New York Times and stating publicly that he was trying to undermine the government of the United States Philip: What did he disseminate that he was legally not allowed to do? Jennings: Great thing to find out Phillip: He wrote a book. What’s the allegation? There not allowed to talk about their experiences when they leave government? Jennigs: I’m saying he used his position to try to undermine the sitting president..

Acyn

445,603 views • 1 year ago

Jennifer Lawrence says she was set to do Bear Grylls until her OB/GYN shut it down over text "I tried to go on Bear Grylls. What happened was I was determined to do it. I ended up getting pregnant, but I was still going to do it" "And then I texted my OB/GYN and I was like, hey, so I'm going to be doing Bear Grylls on like the 17th, is there anything I should tell them? And he was like, you're not doing that. And I was like, oh"

Jennifer Lawrence says she was set to do Bear Grylls until her OB/GYN shut it down over text "I tried to go on Bear Grylls. What happened was I was determined to do it. I ended up getting pregnant, but I was still going to do it" "And then I texted my OB/GYN and I was like, hey, so I'm going to be doing Bear Grylls on like the 17th, is there anything I should tell them? And he was like, you're not doing that. And I was like, oh"

sara

2,841,247 views • 27 days ago

🦌 “what’s that scar?” ask shim ricky about it…. i got it while messing around with shim ricky, i was playing around with shim ricky and i ended up with a scar… yeah… we were playing tag, and i ran into something. i crashed into it, and it hurt, so i was like, “ah..!!” so he was like, “qubing… are you okay?” i was like, “no, i ran into it myself so it’s okay~” so he was like, “i’m sorry… that looks really painful…” and i was like, “no, it's fine~” then on kakaotalk… it was night back then, and when i went into the room and saw it under the light and it looked pretty serious… so i texted him, “hey ricky, i think this is pretty bad…” and he went “oh.. i’m sorry…” and i told him “i’m joking!” … HAHAHA… that’s what happened

🦌 “what’s that scar?” ask shim ricky about it…. i got it while messing around with shim ricky, i was playing around with shim ricky and i ended up with a scar… yeah… we were playing tag, and i ran into something. i crashed into it, and it hurt, so i was like, “ah..!!” so he was like, “qubing… are you okay?” i was like, “no, i ran into it myself so it’s okay~” so he was like, “i’m sorry… that looks really painful…” and i was like, “no, it's fine~” then on kakaotalk… it was night back then, and when i went into the room and saw it under the light and it looked pretty serious… so i texted him, “hey ricky, i think this is pretty bad…” and he went “oh.. i’m sorry…” and i told him “i’m joking!” … HAHAHA… that’s what happened

🎀

145,668 views • 1 year ago

Draymond Green reflects on punching Jordan Poole: "For five seconds, I forgot where I was" “I've had a bunch of situations like that growing up. Sometimes I was the guy who get hit, sometimes I wasn't. Regardless, we move on. That's how I've always approached it” “So when that situation happened, I'm like, all right, cool. We move on. And then when we couldn't, I was like, huh?” “For a while, it made me think, man, this dude nothing like me. Because when those things happen, you just move on” “But it taught me so much. It taught me, you're right, he may not be like you. He ain't from where you from. The things you went through, the way you had to come up, he may not have came up like that” “For that five seconds, I forgot where I was at because I immediately went to what I know. But what you know don't really work here” “Everybody says, ‘Oh man, but you was 10 years in. You should know better.’ Still learning nine years in” “It's lessons like that that ultimately make me who I am to this day because, man, I fucked that up”

Draymond Green reflects on punching Jordan Poole: "For five seconds, I forgot where I was" “I've had a bunch of situations like that growing up. Sometimes I was the guy who get hit, sometimes I wasn't. Regardless, we move on. That's how I've always approached it” “So when that situation happened, I'm like, all right, cool. We move on. And then when we couldn't, I was like, huh?” “For a while, it made me think, man, this dude nothing like me. Because when those things happen, you just move on” “But it taught me so much. It taught me, you're right, he may not be like you. He ain't from where you from. The things you went through, the way you had to come up, he may not have came up like that” “For that five seconds, I forgot where I was at because I immediately went to what I know. But what you know don't really work here” “Everybody says, ‘Oh man, but you was 10 years in. You should know better.’ Still learning nine years in” “It's lessons like that that ultimately make me who I am to this day because, man, I fucked that up”

dank

864,985 views • 1 month ago

🎙️: I heard that during casting for this series, the two of you came to the casting together and then ended up really getting the roles, right? Like you partnered up for the casting? BC: At first we tried out teaming up with several other people to see who we got chemistry with so I teamed up with a variety of people and at last, I met--I met Kin. Like, I had a feeling that Kin- I felt the most shy when with him and when I looked at him, it was like we had something similar. I found out later that he's also an athlete. He's an ice hockey player and I'm a racer so we have similar lifestyles. #BarcodeTin #KinThanachai #KissMeRemember

🎙️: I heard that during casting for this series, the two of you came to the casting together and then ended up really getting the roles, right? Like you partnered up for the casting? BC: At first we tried out teaming up with several other people to see who we got chemistry with so I teamed up with a variety of people and at last, I met--I met Kin. Like, I had a feeling that Kin- I felt the most shy when with him and when I looked at him, it was like we had something similar. I found out later that he's also an athlete. He's an ice hockey player and I'm a racer so we have similar lifestyles. #BarcodeTin #KinThanachai #KissMeRemember

🍃 ยู | 𝕪 𝚘 𝚘 𝚕 𝚒 𝚎 ⊹

75,574 views • 8 months ago

Lil Wayne says he became a father at 14 because his mom was lonely after his father died “I was 14. My mom asked for my kid. My dad had just got murdered that year, the same year I blew up” I was a local rapper forever. A tour, back then, would be me going on weekend shows and coming back home for the week and going to school. We got the Universal deal, and I was like, ‘We have a tour coming up.’ When I went on that tour, we was on the road for like six months” “When I came home, she was like, ‘Is this what you're about to be doing? Is this what I should be expecting? You were gone for too long. I'm lonely. My husband's gone’” “She was like, ‘Listen, let's have a sit down. Me, you, and Toya.’ And so we had the sit down”

Lil Wayne says he became a father at 14 because his mom was lonely after his father died “I was 14. My mom asked for my kid. My dad had just got murdered that year, the same year I blew up” I was a local rapper forever. A tour, back then, would be me going on weekend shows and coming back home for the week and going to school. We got the Universal deal, and I was like, ‘We have a tour coming up.’ When I went on that tour, we was on the road for like six months” “When I came home, she was like, ‘Is this what you're about to be doing? Is this what I should be expecting? You were gone for too long. I'm lonely. My husband's gone’” “She was like, ‘Listen, let's have a sit down. Me, you, and Toya.’ And so we had the sit down”

dank

7,490,104 views • 12 days ago

Mia Malkova revealed that one scene completely changed her perspective on size after working with one of the industry’s most well-known performers. 😳 She admitted she thought she knew what she was signing up for, but the experience turned out to be far more intimidating than she expected. According to Mia, the scene gave her massive anxiety, was painful to film, and made her realize extreme size simply wasn’t for her. “I signed for it. I knew what I was doing… but it was so scary. I thought I was gonna like it, but I hated it.”

Sensitive content

Mia Malkova revealed that one scene completely changed her perspective on size after working with one of the industry’s most well-known performers. 😳 She admitted she thought she knew what she was signing up for, but the experience turned out to be far more intimidating than she expected. According to Mia, the scene gave her massive anxiety, was painful to film, and made her realize extreme size simply wasn’t for her. “I signed for it. I knew what I was doing… but it was so scary. I thought I was gonna like it, but I hated it.”

SayoClips

39,396 views • 4 days ago

Albert Breer on what #Chiefs DC Steve Spagnuolo said to him after the Super Bowl about Brock Purdy: “That conversation I had with Steve Spagnuolo after the game, on his own he said 'Brock Purdy is really good'. When he was referencing why he changed what he was doing in the middle of the game and came off of playing so much zone and went exclusively to man coverage, he was like 'Purdy was identifying what we were doing and ripping apart our zone. We could not stay in that defense because of who Brock Purdy was as a player. So we had to put more on our corners and play more man defense.' You know it wound up working out for them, but they were adjusting to what Brock Purdy was doing, not the other way around.” via: Rich Eisen Show

Albert Breer on what #Chiefs DC Steve Spagnuolo said to him after the Super Bowl about Brock Purdy: “That conversation I had with Steve Spagnuolo after the game, on his own he said 'Brock Purdy is really good'. When he was referencing why he changed what he was doing in the middle of the game and came off of playing so much zone and went exclusively to man coverage, he was like 'Purdy was identifying what we were doing and ripping apart our zone. We could not stay in that defense because of who Brock Purdy was as a player. So we had to put more on our corners and play more man defense.' You know it wound up working out for them, but they were adjusting to what Brock Purdy was doing, not the other way around.” via: Rich Eisen Show

Coach Yac 🗣

903,149 views • 2 years ago

Stallone reveals Dolph Lundgren hit him so hard filming Rocky IV that he ended up in the hospital for 9 days Host: “Dolph Lundgren, you told him to hit you and you ended up in the hospital for 9 days.” Stallone: “He almost killed me. Yeah. That was a freakish accident. It was just freakish.” Stallone: “I did ask for it, but I didn't think he'd hit so hard, you know.” Stallone: “I think I talk to my wife every day about it. Absolutely not worth it in the sense that you don't know when to quit. I should have stopped right before the first Expendables. That's what did me in. I was never whole from that point on.”

Stallone reveals Dolph Lundgren hit him so hard filming Rocky IV that he ended up in the hospital for 9 days Host: “Dolph Lundgren, you told him to hit you and you ended up in the hospital for 9 days.” Stallone: “He almost killed me. Yeah. That was a freakish accident. It was just freakish.” Stallone: “I did ask for it, but I didn't think he'd hit so hard, you know.” Stallone: “I think I talk to my wife every day about it. Absolutely not worth it in the sense that you don't know when to quit. I should have stopped right before the first Expendables. That's what did me in. I was never whole from that point on.”

Zeus

342,937 views • 4 days ago

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 views • 3 years ago

mingyu brings up why he clashes with s.coups! our worry king and positivity king 😂😭 #에스쿱스 🐶 we click the best but also clash the most 🐶 he worries a lot. for example, if we’re taking a taxi to gangnam, he’s like, “do you have taxi fare? what if we can’t catch a cab?” he worries that far ahead. 🐶 but i’m like, “let’s go!” that’s my style. that’s what happens. so i look at him like.. “hyung, you don’t have to go that far. nothing’s gonna happen, we’ll be fine. don’t worry.” then he goes, “what if things go wrong?” he’s like that. 🐶 so that day too, it was a fight between negativity and positivity.

mingyu brings up why he clashes with s.coups! our worry king and positivity king 😂😭 #에스쿱스 🐶 we click the best but also clash the most 🐶 he worries a lot. for example, if we’re taking a taxi to gangnam, he’s like, “do you have taxi fare? what if we can’t catch a cab?” he worries that far ahead. 🐶 but i’m like, “let’s go!” that’s my style. that’s what happens. so i look at him like.. “hyung, you don’t have to go that far. nothing’s gonna happen, we’ll be fine. don’t worry.” then he goes, “what if things go wrong?” he’s like that. 🐶 so that day too, it was a fight between negativity and positivity.

🍒

18,413 views • 1 month ago

Phillip: You are strongly criticizing AOC. Trump stood next to someone from the EU and called them the PM of the UK. He called South America, South Africa. He called Greenland, Iceland. What do you think should happen as a result of his bad answers? O’Leary: AOC wants to become the president. He already is Phillip: What about Donald Trump in 2024 when running for president said: I think Taiwan should pay us for defense? I don't think that we're any different from an insurance policy. Why are we doing this?

Phillip: You are strongly criticizing AOC. Trump stood next to someone from the EU and called them the PM of the UK. He called South America, South Africa. He called Greenland, Iceland. What do you think should happen as a result of his bad answers? O’Leary: AOC wants to become the president. He already is Phillip: What about Donald Trump in 2024 when running for president said: I think Taiwan should pay us for defense? I don't think that we're any different from an insurance policy. Why are we doing this?

Acyn

451,475 views • 5 months ago

“K1 De Ultimate to me is a wonderful person, when we wanted to use him, we collected his address and went to Ijebu, when we got there, the respect Wasiu Ayinde accorded me is different from what i always hear about him before that day, honestly i was overwhelmed. when wanted to go in his compound and they were using metal detector on us, he said they should leave me and said i should come up and we’ve never met before. the reception he gave us was wonderful, he cooked for us, when i was thanking him that he treated us so special, he said the person that brought us is special too. from that day till today, i love Kwam1, he’s a wonderful person and he was even talking about most of my films there that day…” - Nollywood actor, Femi Bright says.

“K1 De Ultimate to me is a wonderful person, when we wanted to use him, we collected his address and went to Ijebu, when we got there, the respect Wasiu Ayinde accorded me is different from what i always hear about him before that day, honestly i was overwhelmed. when wanted to go in his compound and they were using metal detector on us, he said they should leave me and said i should come up and we’ve never met before. the reception he gave us was wonderful, he cooked for us, when i was thanking him that he treated us so special, he said the person that brought us is special too. from that day till today, i love Kwam1, he’s a wonderful person and he was even talking about most of my films there that day…” - Nollywood actor, Femi Bright says.

last born

22,007 views • 3 months ago