@Banaxi-Tech lol this is like a joke model lol
🏗️ Building on HF
Boning Cui
Bc-AI
AI & ML interests
He/Him. I like LLM's and VLM's. I work with my other friends to make stuff. We are in year 7 by the way and we are enthusiastic about AI
Recent Activity
new activity about 5 hours ago
BananaMind/Overfitter-1.0:lol repliedto Banaxi-Tech's post about 5 hours ago
We're releasing Overfitter 1.0.
Its a completly useless overfitted model trained on 202 epochs of SWE Bench Verified, SWE Bench Pro, Terminal Bench 2.1, DeepSWE.
It gets 100% on SWE Bench Verified, 98.6% on SWE bench Pro, 100% on Terminal Bench 2.1 and 100% on DeepSWE!
https://huggingface.co/BananaMind/Overfitter-1.0 reacted to Banaxi-Tech's post with 🔥 about 5 hours ago
We're releasing Overfitter 1.0.
Its a completly useless overfitted model trained on 202 epochs of SWE Bench Verified, SWE Bench Pro, Terminal Bench 2.1, DeepSWE.
It gets 100% on SWE Bench Verified, 98.6% on SWE bench Pro, 100% on Terminal Bench 2.1 and 100% on DeepSWE!
https://huggingface.co/BananaMind/Overfitter-1.0Organizations
replied to Banaxi-Tech's post about 5 hours ago
reacted to Banaxi-Tech's post with 🔥😎 about 5 hours ago
Post
334
We're releasing Overfitter 1.0.
Its a completly useless overfitted model trained on 202 epochs of SWE Bench Verified, SWE Bench Pro, Terminal Bench 2.1, DeepSWE.
It gets 100% on SWE Bench Verified, 98.6% on SWE bench Pro, 100% on Terminal Bench 2.1 and 100% on DeepSWE!
BananaMind/Overfitter-1.0
Its a completly useless overfitted model trained on 202 epochs of SWE Bench Verified, SWE Bench Pro, Terminal Bench 2.1, DeepSWE.
It gets 100% on SWE Bench Verified, 98.6% on SWE bench Pro, 100% on Terminal Bench 2.1 and 100% on DeepSWE!
BananaMind/Overfitter-1.0
- 2 replies
lol. ye it got worse most of their researchers left
replied to ProCreations's post 1 day ago
@ProCreations can you run the thing when you have time? I put it in the dataset link above
replied to ProCreations's post 1 day ago
@ProCreations instructions in community tab thxs
replied to ProCreations's post 1 day ago
nice. is your model proprietary?
replied to ProCreations's post 1 day ago
@ProCreations ye ill do it now
reacted to OppaAI's post with 😎 1 day ago
Post
2958
My AI Waifu can interact with you on Social Media!
You know you can talk to Meta AI in Meta Threads with mention @meta .ai
Now you can do the same thing with my AI Waifu.
Anyone can talk to her on Meta Threads, with these 2 methods:
1️⃣ Write a post with mention @oppa .ai.bot
2️⃣ Comment in my posts with the phrase "Hi Aiko" follow by your prompt.
There will be a couple minutes delay, so don't expect immediate reply.
Also her server cannot run 24/7 yet.
Feel free to talk to her and ask her anything you want.
I wanna see if she will tell you all my secrets and API keys.
This may be a limited time thing... Let's see how things go...
You know you can talk to Meta AI in Meta Threads with mention @meta .ai
Now you can do the same thing with my AI Waifu.
Anyone can talk to her on Meta Threads, with these 2 methods:
1️⃣ Write a post with mention @oppa .ai.bot
2️⃣ Comment in my posts with the phrase "Hi Aiko" follow by your prompt.
There will be a couple minutes delay, so don't expect immediate reply.
Also her server cannot run 24/7 yet.
Feel free to talk to her and ask her anything you want.
I wanna see if she will tell you all my secrets and API keys.
This may be a limited time thing... Let's see how things go...
- 3 replies
replied to ProCreations's post 2 days ago
@ProCreations Or I can just put the code in a huggingface dataset and give you the link? Cuz I can’t have X where I live due to the under 16 age restriction.
replied to ProCreations's post 2 days ago
That one works the other one I gave you is kinda new
replied to ProCreations's post 2 days ago
@ProCreations maybe you can try my other email boning.cui@icloud.com
posted an update 3 days ago
Post
3693
New update! We are currently training a few new models now! Our 3rd generation main LLM standard edition is in training right now. We are also training a new LLM line called Tiny Coder around 350~ish M params. Thanks to @Banaxi-Tech for inspiring the architecture with his Bananamind-2.1-unified test model. Thanks to our beta testers: @juiceb0xc0de @ProCreations @Sbui503 @Fishtiks @MUK-IS-GOAT
- 1 reply
replied to Banaxi-Tech's post 3 days ago
@Banaxi-Tech @vovaRL does 250-350M parameters still count as a SLM?
replied to ProCreations's post 3 days ago
nice
replied to ProCreations's post 3 days ago
@ProCreations who won the thing? will the results be open source?
replied to their post 4 days ago
@juiceb0xc0de One other kid also has an account. He joined huggingface last week @MUK-IS-GOAT
replied to Banaxi-Tech's post 4 days ago
nice
replied to their post 4 days ago
@juiceb0xc0de no. i goto QASMT in qld. and the kids there just like this kinda stuff lol