here if you want to see https://banaxi-tech-bananamind-codeq-1-3-2b-training.hf.space/
Banaxi PRO
Banaxi-Tech
AI & ML interests
SLMs, training from scratch, LoRA, TTS, Ternary models. AI Interpretability. BCI. Contact at banaxitech@gmail.com
Recent Activity
new activity about 3 hours ago
BananaMind/BananaMind-CodeQ-1.3-2B:bruh no way you used lora updated a model about 4 hours ago
BananaMind/BananaMind-CodeQ-1.3-2B liked a model about 7 hours ago
TobiasLogic/cagliostro-v3Organizations
replied to DedeProGames's post about 12 hours ago
replied to DedeProGames's post about 13 hours ago
We're already making 2B!
replied to DedeProGames's post about 14 hours ago
What hardware do you have so which model size could you comfortably run? We could make a new model for that if its common
replied to DedeProGames's post about 14 hours ago
But they will be good!
replied to DedeProGames's post about 14 hours ago
The QEDOC ANANAB DNIM
Its our new bananamind code q models
replied to DedeProGames's post about 14 hours ago
Minicpm5 2b is good base and ornith 1.5 9b
replied to DedeProGames's post about 14 hours ago
Nah
replied to their post about 14 hours ago
replied to their post about 23 hours ago
Stop this hidden.
replied to DedeProGames's post 1 day ago
Oh yeah you dont have gpu but yeah MAYBE we will try one on BananaMind 2 Pro
replied to DedeProGames's post 1 day ago
which model size you like the most we could make a CodeQ for that too!
replied to DedeProGames's post 1 day ago
yea normal at the start and for distilattion like my Lora is 200M params
replied to DedeProGames's post 1 day ago
@GGUFGuy it keeps changing its at ~25% rn
replied to DedeProGames's post 1 day ago
I type soo fast
do the 1 minute and medium and give me your results https://www.typingtest.com/
replied to DedeProGames's post 1 day ago
@GGUFGuy here for BananaMind CodeQ 1.3 2B https://banaxi-tech-bananamind-codeq-1-3-2b-training.hf.space/
reacted to their post with ➕ 1 day ago
Post
956
Hi everyone!
We've seen some people getting confused with the BananaMind Leaderboards so ill explain!
We have 2 leaderboards, THESE are NOT the same, first BananaMind/BananaMindBench-Leaderboard which is ONLY for BananaMind Base Bench 1.1. The 10/10 scores do NOT mean that the benchmark is saturated. It isnt saturated, these models score 10/10 because they are the current best models, our /10 ranking system works by taking the ELO scores and then comparing them to the scores in the same size range. So if a better model releases that gets 10/10 and the others get lower.
And we also have the BananaMind SLM leaderboard, not the BananaMindBench leaderboard which uses ARC EASY,PIQA,Hellaswag, Arithmark 3 and the BananaMind Base Bench 1.1. This is the newer and recommended version.
Hope you understand it now!
cODeQ
We've seen some people getting confused with the BananaMind Leaderboards so ill explain!
We have 2 leaderboards, THESE are NOT the same, first BananaMind/BananaMindBench-Leaderboard which is ONLY for BananaMind Base Bench 1.1. The 10/10 scores do NOT mean that the benchmark is saturated. It isnt saturated, these models score 10/10 because they are the current best models, our /10 ranking system works by taking the ELO scores and then comparing them to the scores in the same size range. So if a better model releases that gets 10/10 and the others get lower.
And we also have the BananaMind SLM leaderboard, not the BananaMindBench leaderboard which uses ARC EASY,PIQA,Hellaswag, Arithmark 3 and the BananaMind Base Bench 1.1. This is the newer and recommended version.
Hope you understand it now!
cODeQ
- 12 replies
posted an update 1 day ago
Post
956
Hi everyone!
We've seen some people getting confused with the BananaMind Leaderboards so ill explain!
We have 2 leaderboards, THESE are NOT the same, first BananaMind/BananaMindBench-Leaderboard which is ONLY for BananaMind Base Bench 1.1. The 10/10 scores do NOT mean that the benchmark is saturated. It isnt saturated, these models score 10/10 because they are the current best models, our /10 ranking system works by taking the ELO scores and then comparing them to the scores in the same size range. So if a better model releases that gets 10/10 and the others get lower.
And we also have the BananaMind SLM leaderboard, not the BananaMindBench leaderboard which uses ARC EASY,PIQA,Hellaswag, Arithmark 3 and the BananaMind Base Bench 1.1. This is the newer and recommended version.
Hope you understand it now!
cODeQ
We've seen some people getting confused with the BananaMind Leaderboards so ill explain!
We have 2 leaderboards, THESE are NOT the same, first BananaMind/BananaMindBench-Leaderboard which is ONLY for BananaMind Base Bench 1.1. The 10/10 scores do NOT mean that the benchmark is saturated. It isnt saturated, these models score 10/10 because they are the current best models, our /10 ranking system works by taking the ELO scores and then comparing them to the scores in the same size range. So if a better model releases that gets 10/10 and the others get lower.
And we also have the BananaMind SLM leaderboard, not the BananaMindBench leaderboard which uses ARC EASY,PIQA,Hellaswag, Arithmark 3 and the BananaMind Base Bench 1.1. This is the newer and recommended version.
Hope you understand it now!
cODeQ
- 12 replies
replied to DedeProGames's post 1 day ago
i can just slower
replied to DedeProGames's post 1 day ago
ik but you have compute?
replied to DedeProGames's post 1 day ago
we really need some compute