Post
132
bci is the future.
and i dont like that
and i dont like that
- 4 replies
AI & ML interests
None yet
Recent Activity
View all activity
Banaxi-Techย
posted an update 1 day ago
Banaxi-Techย
posted an update 2 days ago
Post
7,043
hi everyone
we at
klein-ml are announcing KleinMem
These models will have Native memory, without any system-prompt or prompt, it still remembers exactly.
Get early access at https://tinyurl.com/klein-eap limited to 15 users.
Architecture details are coming soon toon.
If you know alot about architecture and want to help build it, join klein-ml .
we at
These models will have Native memory, without any system-prompt or prompt, it still remembers exactly.
Get early access at https://tinyurl.com/klein-eap limited to 15 users.
Architecture details are coming soon toon.
If you know alot about architecture and want to help build it, join
Banaxi-Techย
posted an update 3 days ago
Post
3,759
KV1 updates:
We at klein-ml have finished stage 1 of KV1 1.2B, we don't think we will need additional stages.
KV1 2.6B is near the midpoint of training, going well so far, its going to be our most agentic model yet.
We have released Klein Code Bench klein-ml/klein-code-bench, a benchmark testing whether models can build complete projects from scratch. It contains a easy, intermediate, hard and max subset.
Here are some benchmarks of the current KV1 1.2B
It retains 75.8% of FP16 intelligence.
We are also announcing that we at klein-ml are working on Klein 24B A2B which will be our first model featuring ternary weight quantization.
We at
KV1 2.6B is near the midpoint of training, going well so far, its going to be our most agentic model yet.
We have released Klein Code Bench klein-ml/klein-code-bench, a benchmark testing whether models can build complete projects from scratch. It contains a easy, intermediate, hard and max subset.
Here are some benchmarks of the current KV1 1.2B
It retains 75.8% of FP16 intelligence.
We are also announcing that we at
- 2 replies
Banaxi-Techย
posted an update 5 days ago
Post
2,253
We're announcing KV1. Now.
We're going to take some models, do a bit of continued training on them and QAT them for only a 2 bit KV cache.
And because of what happened with BGA, and this is also kind of some research stuff, here's what we're going to change:
We're going to always, before we release how and make any claims, release our results.
We also would like (idk if we can) to have some external reviewers before releasing them, I'M talking to YOU @AtAndDev and @mithulaartigala
And we're going to properly cite other research.
The models we are going to release is:
KV1 1.2B, based on LFM 2.5 1.2B Instruct
KV1 2.6B, based on LFM 2.5 2.6B Instruct
KV1 4B, based on Qwen3.5 4B.
If we get enough compute, we may also train:
KV1 9B
And if you guys want to a ~27B model, you guys decide which, either on LFM 2.5 24B A2B, Qwen3.8 27B, or Qwen3.6 35B A3B.
Our goal is to get 2 bit, at 4 bit quality.
Here's an image of our current progress, KV1 is at 3 bit, not 4 bit, but it will improve!
We're going to take some models, do a bit of continued training on them and QAT them for only a 2 bit KV cache.
And because of what happened with BGA, and this is also kind of some research stuff, here's what we're going to change:
We're going to always, before we release how and make any claims, release our results.
We also would like (idk if we can) to have some external reviewers before releasing them, I'M talking to YOU @AtAndDev and @mithulaartigala
And we're going to properly cite other research.
The models we are going to release is:
KV1 1.2B, based on LFM 2.5 1.2B Instruct
KV1 2.6B, based on LFM 2.5 2.6B Instruct
KV1 4B, based on Qwen3.5 4B.
If we get enough compute, we may also train:
KV1 9B
And if you guys want to a ~27B model, you guys decide which, either on LFM 2.5 24B A2B, Qwen3.8 27B, or Qwen3.6 35B A3B.
Our goal is to get 2 bit, at 4 bit quality.
Here's an image of our current progress, KV1 is at 3 bit, not 4 bit, but it will improve!
- 43 replies
Banaxi-Techย
posted an update 6 days ago
Post
4,212
Should I even continue making models?
- 27 replies
Banaxi-Techย
posted an update 7 days ago
Post
4,521
Hi everyone, we're back!
And we're releasing something major again now, if you have seen Grok Bot, its very powerful, but there isn't really a local alternative yet.
Today we're releasing Minds, they're personal AI bots that live on your computer.
They can run anywhere, on your phone, on your mac, on windows, and even on linux.
They support OpenAI Oauth as the main integration because most people already have a ChatGPT sub.
But locally, It supports ANY openai compatible api which allows you to setup ollama and llama.cpp and everything else.
It uses Jev for command approval on OpenRouter and Muse Spark Transcribe for transcription.
Its fully Open Source!
Check it out: https://github.com/BananaMind/Minds
And we're releasing something major again now, if you have seen Grok Bot, its very powerful, but there isn't really a local alternative yet.
Today we're releasing Minds, they're personal AI bots that live on your computer.
They can run anywhere, on your phone, on your mac, on windows, and even on linux.
They support OpenAI Oauth as the main integration because most people already have a ChatGPT sub.
But locally, It supports ANY openai compatible api which allows you to setup ollama and llama.cpp and everything else.
It uses Jev for command approval on OpenRouter and Muse Spark Transcribe for transcription.
Its fully Open Source!
Check it out: https://github.com/BananaMind/Minds
- 9 replies
Post
5,200
@Banaxi-Tech stop hiding my comments. AND STOP STEALING PAPERS AND SPREADING MISINFORMATION.
your BGA blog is a copy of NSA (deepseek, 2025) branded under your name. literally the same top16 selected blocks, 512 local window, router over block summaries, all you did was change block size from 64 to 128.
you didnt cite NSA once but you put a โplease cite BGAโ bibtex at the bottom.
i commented under your post and said that there is no way that you can support claims like: โThe Accuracy Should BE WAy better than DSA but untested yet.โ you didnt run a single experiment. and the 256x isnt from BGA, its just n/2k with k=2048 so the exact same k DSA uses. if opus wrote this for you, at least read it before posting.
i commented again after you hid my comment despite it having constructive and correct feedback and you hid that too. and again.
you can hide the truth and just try to get hf post likes..... but is it really the thing that needs to be done? do you really want to take papers and make them yours while barely even changing the params?
admitting your mistakes and doing something about them needs humbleness, intelligence, humanness.
i encourage you to admit your mistakes and try to do better next time (at least read what blog your ai wrote or do proper experiments to back your stuff up).
your BGA blog is a copy of NSA (deepseek, 2025) branded under your name. literally the same top16 selected blocks, 512 local window, router over block summaries, all you did was change block size from 64 to 128.
you didnt cite NSA once but you put a โplease cite BGAโ bibtex at the bottom.
i commented under your post and said that there is no way that you can support claims like: โThe Accuracy Should BE WAy better than DSA but untested yet.โ you didnt run a single experiment. and the 256x isnt from BGA, its just n/2k with k=2048 so the exact same k DSA uses. if opus wrote this for you, at least read it before posting.
i commented again after you hid my comment despite it having constructive and correct feedback and you hid that too. and again.
you can hide the truth and just try to get hf post likes..... but is it really the thing that needs to be done? do you really want to take papers and make them yours while barely even changing the params?
admitting your mistakes and doing something about them needs humbleness, intelligence, humanness.
i encourage you to admit your mistakes and try to do better next time (at least read what blog your ai wrote or do proper experiments to back your stuff up).
- 49 replies
Banaxi-Techย
posted an update 8 days ago
Post
4,690
Well GPT X3 takes the lead. As of right now.
We are now announcing BananaMind 3 ๐! (not ai for those emoji guys)
All models will use BGA (which is almost just NSA) and our BM3X architecture.
Its sizes will be:
BananaMind 3 Flash Lite, 3M parameters at a context of 8K context.
BananaMind 3 Lite, 10M parameters with 16K context.
BananaMind 3 Flash, 25M Parameters with 16K context.
BananaMind 3 Pro, 50M parameters with 24K context.
BananaMind 3 Ultra, 100M parameters with 32K context.
And lastly, BananaMind 3 Max with 150M parameters and 64K CONTEXT.
I can assure you BananaMind 3 Max WILL beat GPT X3 or match it, we won't release it otherwise. We hope for a 40+ INTELLIGENCE INDEX!
BananaMind 3 may also be partnered with dot labs.
We will cancel BananaMind 2.1 and BananaMind 2 Ultra.
As of the BETU SLM Leaderboard we may need to release it after October 11, im very busy right now (even though we said We will release BETU leaderboard before Oct 11 ๐)
We are now announcing BananaMind 3 ๐! (not ai for those emoji guys)
All models will use BGA (which is almost just NSA) and our BM3X architecture.
Its sizes will be:
BananaMind 3 Flash Lite, 3M parameters at a context of 8K context.
BananaMind 3 Lite, 10M parameters with 16K context.
BananaMind 3 Flash, 25M Parameters with 16K context.
BananaMind 3 Pro, 50M parameters with 24K context.
BananaMind 3 Ultra, 100M parameters with 32K context.
And lastly, BananaMind 3 Max with 150M parameters and 64K CONTEXT.
I can assure you BananaMind 3 Max WILL beat GPT X3 or match it, we won't release it otherwise. We hope for a 40+ INTELLIGENCE INDEX!
BananaMind 3 may also be partnered with dot labs.
We will cancel BananaMind 2.1 and BananaMind 2 Ultra.
As of the BETU SLM Leaderboard we may need to release it after October 11, im very busy right now (even though we said We will release BETU leaderboard before Oct 11 ๐)
- 12 replies
Banaxi-Techย
posted an update 10 days ago
Post
3,225
We have released BGA!
And wow, It provides 256x (and 512x at the end of 1M) yes 256x LESS attention compute at 1M context window.
That means you can train a 1M context window at the compute of a ~4K context window.
Check IT OUT: BananaMind/blog
The Accuracy Should BE WAy better than DSA but untested yet.
And, now some updates on BananaMind 3:
BananaMind 3 Will start training Soon!
Sizes: 10M, 25M, 50M, 100M, 150M
And the context windows ARE INSANE: 10M, 16K context, 25M 16k context, 50M 32K context, 100M and 150M, 64K context!!!!
And wow, It provides 256x (and 512x at the end of 1M) yes 256x LESS attention compute at 1M context window.
That means you can train a 1M context window at the compute of a ~4K context window.
Check IT OUT: BananaMind/blog
The Accuracy Should BE WAy better than DSA but untested yet.
And, now some updates on BananaMind 3:
BananaMind 3 Will start training Soon!
Sizes: 10M, 25M, 50M, 100M, 150M
And the context windows ARE INSANE: 10M, 16K context, 25M 16k context, 50M 32K context, 100M and 150M, 64K context!!!!
- 13 replies
Banaxi-Techย
posted an update 11 days ago
Post
134
Hi! We're right now experimenting with so many new architectures!
We are also going to release BananaMind Gate Attention very soon, its a new attention that can make attention 128x cheaper at 1M Context! Check my account for HF blogs it will release there!
We are also going to release BananaMind Gate Attention very soon, its a new attention that can make attention 128x cheaper at 1M Context! Check my account for HF blogs it will release there!
prithivMLmodsย
posted an update 12 days ago
Post
4,136
OneDecision-VisionGuard-Demo is now available on Hugging Face Spaces!
๐ค Space: prithivMLmods/OneDecision-VisionGuard-Demo
This demo showcases the OneDecision-VisionGuard family of multimodal image classification models for detecting NSFW and other sensitive visual content, with structured JSON reasoning, improved accuracy, and better handling of edge cases such as sensitive imagery, uncensored analysis, scene descriptions, and classification reasoning.
๐ฆ Models: 27B, 9B, 4B โ prithivMLmods/OneDecision-VisionGuard-27B-SFT, prithivMLmods/OneDecision-VisionGuard-9B-SFT, prithivMLmods/OneDecision-VisionGuard-4B-SFT
โ๏ธ Collection: https://huggingface.co/collections/prithivMLmods/onedecision-visionguard
To learn more, visit the app page or the respective model pages.
๐ค Space: prithivMLmods/OneDecision-VisionGuard-Demo
This demo showcases the OneDecision-VisionGuard family of multimodal image classification models for detecting NSFW and other sensitive visual content, with structured JSON reasoning, improved accuracy, and better handling of edge cases such as sensitive imagery, uncensored analysis, scene descriptions, and classification reasoning.
๐ฆ Models: 27B, 9B, 4B โ prithivMLmods/OneDecision-VisionGuard-27B-SFT, prithivMLmods/OneDecision-VisionGuard-9B-SFT, prithivMLmods/OneDecision-VisionGuard-4B-SFT
โ๏ธ Collection: https://huggingface.co/collections/prithivMLmods/onedecision-visionguard
To learn more, visit the app page or the respective model pages.
Banaxi-Techย
posted an update 12 days ago
Post
88
We're introducing ACR 1.0.
We trained this model on a 5070 Ti for weeks, here are some of the architecture details:
57M parameters, with one M and one G stream.
When we tested it on benchmarks, we got these results:
Benchmark Full G-Only Delta
PIQA 62.24% 53.43% +8.81
ARC-Easy 41.96% 32.28% +9.68
HellaSwag 33.19% 29.08% +4.11
Tiny ToM 40.65% 33.75% +6.90
ArithMark 3.0 33.40% 32.80% +0.60
Base Bench 1.1 51.71% 40.29% +11.42
Check it out at saicr/ACR-1.0
We trained this model on a 5070 Ti for weeks, here are some of the architecture details:
57M parameters, with one M and one G stream.
When we tested it on benchmarks, we got these results:
Benchmark Full G-Only Delta
PIQA 62.24% 53.43% +8.81
ARC-Easy 41.96% 32.28% +9.68
HellaSwag 33.19% 29.08% +4.11
Tiny ToM 40.65% 33.75% +6.90
ArithMark 3.0 33.40% 32.80% +0.60
Base Bench 1.1 51.71% 40.29% +11.42
Check it out at saicr/ACR-1.0
- 3 replies
Banaxi-Techย
posted an update 13 days ago
Banaxi-Techย
posted an update 14 days ago
Post
3,072
We will release the BEST SLM Leaderboard before Oct 11.
It will feature everything:
Easy to use model picker.
EXTREMELY Easy way to add your own models (2 click)
MULTIPLE leaderboard for different model types
And more!
So why don't you help us build it?
Join
betu-slm-leaderboard-testers
It will feature everything:
Easy to use model picker.
EXTREMELY Easy way to add your own models (2 click)
MULTIPLE leaderboard for different model types
And more!
So why don't you help us build it?
Join
- 3 replies
Banaxi-Techย
posted an update 17 days ago
Banaxi-Techย
posted an update 21 days ago
Post
7,629
We're releasing a MAJOR update to the BananaAll SLM Super App.
If you want to use a custom architecture, previously you had to go trough reviewing the code yourself, now add an Openrouter API key and review it with GPT 6 Luna in one button. A review cost be half a cent so anyone can try it. This is one of the main features.
Now ROCm, AMD and Windows, Mac support.
Colab and Molab support.
Detailed list of features:
Get improved Windows Python detection and support paths for compatible AMD ROCm, Intel XPU, and Apple MPS setups.
Choose local training or export a self-contained Python script for Colab or Molab. Notebook runs produce a downloadable model ZIP.
Start pretraining with an existing modelโs tokenizer, or train a new one from your datasets.
Try experimental 1.58-bit Ternary fake-quantized training on NVIDIA GPUs.
Watch live tokens per second. Model compilation is on by default and falls back automatically if it fails.
Build custom architectures with separate configuration and modeling files, then review the training code manually or with optional OpenRouter AI Review.
Install from source with the new coding-agent instructions.
This release also fixes inflated loss reporting for custom models.
And for those users who didn't want to try it out just because installation would be so hard, it isnt now.
Go to any coding agent (Pi, Claude Code, Codex, OpenCode, basically all work), and just paste "Install BananaAll for me. Fetch and follow https://raw.githubusercontent.com/BananaMind/BananaAll/main/agent_install.txt."
That's it.
Check it out at https://github.com/BananaMind/BananaAll/
Also on SAICR, we're currently training a new major model (NACR v2) and ACR 1.0 is in the finishing.
If you want to use a custom architecture, previously you had to go trough reviewing the code yourself, now add an Openrouter API key and review it with GPT 6 Luna in one button. A review cost be half a cent so anyone can try it. This is one of the main features.
Now ROCm, AMD and Windows, Mac support.
Colab and Molab support.
Detailed list of features:
Get improved Windows Python detection and support paths for compatible AMD ROCm, Intel XPU, and Apple MPS setups.
Choose local training or export a self-contained Python script for Colab or Molab. Notebook runs produce a downloadable model ZIP.
Start pretraining with an existing modelโs tokenizer, or train a new one from your datasets.
Try experimental 1.58-bit Ternary fake-quantized training on NVIDIA GPUs.
Watch live tokens per second. Model compilation is on by default and falls back automatically if it fails.
Build custom architectures with separate configuration and modeling files, then review the training code manually or with optional OpenRouter AI Review.
Install from source with the new coding-agent instructions.
This release also fixes inflated loss reporting for custom models.
And for those users who didn't want to try it out just because installation would be so hard, it isnt now.
Go to any coding agent (Pi, Claude Code, Codex, OpenCode, basically all work), and just paste "Install BananaAll for me. Fetch and follow https://raw.githubusercontent.com/BananaMind/BananaAll/main/agent_install.txt."
That's it.
Check it out at https://github.com/BananaMind/BananaAll/
Also on SAICR, we're currently training a new major model (NACR v2) and ACR 1.0 is in the finishing.
- 11 replies
Post
1,787
Just launched Qwen Image 2.1 Uncensored All-In-One LoRA Studio on @huggingface #ZeroGPU! Includes 15+ on-demand
LoRAs (Turbo 4-step, Anime, Photoreal, FaceSwap) with 0 data retention: arudradey/qwen-image-2.1-uncensored-aio-loras
LoRAs (Turbo 4-step, Anime, Photoreal, FaceSwap) with 0 data retention: arudradey/qwen-image-2.1-uncensored-aio-loras
Banaxi-Techย
posted an update 23 days ago
Post
4,877
We're excited to release BananaAll, our SLM Super App.
It allows you to do EVERYTHING you need to do to trains SLMs in a single app, no terminal, no 30 chrome tabs.
The train tab allows you to train models, select datasets from presets, and use other ones with auto mapping, model size slider, it automatically generates a training script for you.
Then after you've trained the model or want to compare it to competitors, the evaluation tab, run ARC EASY, ARC Challenge, Hellaswag, PIQA, Arithmark 3, BananaMind Base Bench and more! Simple Results screen.
And lastly the inference tab, run your trained models or others.
Normally you would need seperate apps or scripts for that, but the BananaAll Super App lets you do all of that in a single app.
We also trained a small 2.5M parameter model on 200M tokens of Fineweb edu, The results: BananaMind Base Bench 854 and 53% on PIQA. On only 200M tokens.
Check it out at https://github.com/BananaMind/BananaAll.
It allows you to do EVERYTHING you need to do to trains SLMs in a single app, no terminal, no 30 chrome tabs.
The train tab allows you to train models, select datasets from presets, and use other ones with auto mapping, model size slider, it automatically generates a training script for you.
Then after you've trained the model or want to compare it to competitors, the evaluation tab, run ARC EASY, ARC Challenge, Hellaswag, PIQA, Arithmark 3, BananaMind Base Bench and more! Simple Results screen.
And lastly the inference tab, run your trained models or others.
Normally you would need seperate apps or scripts for that, but the BananaAll Super App lets you do all of that in a single app.
We also trained a small 2.5M parameter model on 200M tokens of Fineweb edu, The results: BananaMind Base Bench 854 and 53% on PIQA. On only 200M tokens.
Check it out at https://github.com/BananaMind/BananaAll.
- 25 replies
Banaxi-Techย
posted an update 24 days ago
Post
1,903
hi everyone
we have released nacr
its not just any model, its nacr
we have 6 more features and this model only uses 20% of its total capacity!
check it out at saicr/nacr
we're currently working on expanding access as we do more research but right now you have to use our gated access form
follow
saicr if you're interested
if you want to join saicr, first read the entire nacr readme, then press the join button.
we have released nacr
its not just any model, its nacr
we have 6 more features and this model only uses 20% of its total capacity!
check it out at saicr/nacr
we're currently working on expanding access as we do more research but right now you have to use our gated access form
follow
if you want to join saicr, first read the entire nacr readme, then press the join button.
- 14 replies
prithivMLmodsย
posted an update 25 days ago
Post
3,930
Qwen-Image-2.1 Plug and Play LoRA App is now live on Hugging Face Spaces.
๐ Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP
It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!
๐ Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP
To learn more, visit the app page or the respective model pages.
๐ Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP
It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!
๐ Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP
To learn more, visit the app page or the respective model pages.