yeah i know, i have my priorities elsewhere
Hoglet (Ash) PRO
Hoglet-33
P(doom) <0.1%
AI & ML interests
Open source AI, datasets, parameter efficiency, SLMs, AI for the betterment of humanity. Contact at ash@basicallyai.co
Recent Activity
repliedto Banaxi-Tech's post about 11 hours ago
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 repliedto Banaxi-Tech's post about 12 hours ago
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 repliedto their post about 15 hours ago
A few questions for everyone:
1. Should I release all Pebble 1.5 models together in one big launch, or release each model individually as it's ready?
2. What would you like to see from the Pebble models? Any specific features, capabilities, or improvements?
3. What would you like to see from basically AI as a company in general?
I'd love to hear your thoughts and suggestions!Organizations
replied to Banaxi-Tech's post about 11 hours ago
replied to Banaxi-Tech's post about 12 hours ago
YAY!
also dang it, i was gonna do that lol. How do you build all of these so quickly?
replied to their post about 15 hours ago
they wont be using NSA i really only heard about NSA after the BGA stuff lol, ive already started training on most of the models to switch, i'll consider it for future models..
replied to their post about 15 hours ago
the largest I'm going to do for 1.5 is 125M, 150M will be later lol
reacted to mithulaartigala's post with 🤗🔥 1 day ago
Post
3287
I am LOVING HuggingFace Pro <3
- 7 replies
posted an update 1 day ago
Post
73
A few questions for everyone:
1. Should I release all Pebble 1.5 models together in one big launch, or release each model individually as it's ready?
2. What would you like to see from the Pebble models? Any specific features, capabilities, or improvements?
3. What would you like to see from basically AI as a company in general?
I'd love to hear your thoughts and suggestions!
1. Should I release all Pebble 1.5 models together in one big launch, or release each model individually as it's ready?
2. What would you like to see from the Pebble models? Any specific features, capabilities, or improvements?
3. What would you like to see from basically AI as a company in general?
I'd love to hear your thoughts and suggestions!
- 4 replies
replied to Banaxi-Tech's post 1 day ago
actually a longer context does not take up more embedding params. though it sometimes can depending on the positional embeddings used; if you are using RoPE more or less context doesnt affect param count. Out of the most popular types only learned absolute embeddings will always create more params whereas relative learned embeddings will sometimes create more. most others dont.
reacted to Banaxi-Tech's post with 👍 10 days ago
reacted to DedeProGames's post with 🔥 14 days ago
Post
2889
🧱 SLM Tetris Arena: can a small language model play Tetris without ever being trained on it?
I built an arena where tiny decoder-only LMs (50K–250M params) play Tetris zero-shot. There is no fine-tuning and no game data. They only use what they picked up from pre-training on text.
How it works:
- For every piece, the engine simulates each legal placement and describes the result in plain English ("clears one line, creates no new holes, keeps the stack low…").
- The model never sees the grid. It reads each description, and the arena compares log P(" good move") with log P(" bad move"). The best-rated placement is played.
- Every player gets the same piece sequence, so it's a fair race.
- There are two protocols: Guided (the rules are in the prompt) and Blind (no rules, only pre-training knowledge).
Two ways to play:
- Match: pick any models (even your own, custom architectures welcome) and watch them play side by side on retro 8-bit boards.
- Ranked: press Play and the arena picks up to 4 models at random from a curated pool of 29. Nobody chooses their opponents, so Elo can't be farmed. Matches run on the server and count even if you close the tab.
First results (~225 ranked matches):
- gpt2 (124M) leads with 1283 Elo, but SupraNeo-4M (4M) is right behind at 1239. Next come LowOnMind-5M and BananaMind-2.1-Pico (1.5M!).
- Model size barely predicts Elo (r ≈ 0.06). Survival does (r ≈ 0.9): the models that avoid holes and keep the stack low are the ones that win.
Every ranked match (seed, model commit SHAs, scores, Elo before/after) is logged in a public dataset.
▶ Play: DedeProGames/SLM-Tetris-Arena
📊 Results: DedeProGames/lm-tetris-arena-results
Want your model in the Ranked pool? Drop it in the comments!
I built an arena where tiny decoder-only LMs (50K–250M params) play Tetris zero-shot. There is no fine-tuning and no game data. They only use what they picked up from pre-training on text.
How it works:
- For every piece, the engine simulates each legal placement and describes the result in plain English ("clears one line, creates no new holes, keeps the stack low…").
- The model never sees the grid. It reads each description, and the arena compares log P(" good move") with log P(" bad move"). The best-rated placement is played.
- Every player gets the same piece sequence, so it's a fair race.
- There are two protocols: Guided (the rules are in the prompt) and Blind (no rules, only pre-training knowledge).
Two ways to play:
- Match: pick any models (even your own, custom architectures welcome) and watch them play side by side on retro 8-bit boards.
- Ranked: press Play and the arena picks up to 4 models at random from a curated pool of 29. Nobody chooses their opponents, so Elo can't be farmed. Matches run on the server and count even if you close the tab.
First results (~225 ranked matches):
- gpt2 (124M) leads with 1283 Elo, but SupraNeo-4M (4M) is right behind at 1239. Next come LowOnMind-5M and BananaMind-2.1-Pico (1.5M!).
- Model size barely predicts Elo (r ≈ 0.06). Survival does (r ≈ 0.9): the models that avoid holes and keep the stack low are the ones that win.
Every ranked match (seed, model commit SHAs, scores, Elo before/after) is logged in a public dataset.
▶ Play: DedeProGames/SLM-Tetris-Arena
📊 Results: DedeProGames/lm-tetris-arena-results
Want your model in the Ranked pool? Drop it in the comments!
- 1 reply
replied to DedeProGames's post 14 days ago
Why do you think that GPT-2 is in the top followed by sub 10M models?
replied to Banaxi-Tech's post 14 days ago
like instead of being locked into gpt6 luna i can use deepseek or claude, or another openai model
replied to their post 14 days ago
oh sorry, i dont understand anything sometimes
replied to Banaxi-Tech's post 14 days ago
I know you have been working a lot on this, and its great, but could you maybe add support for other models so i can choose or use an API key and model from another platform if the platform is OpenAI compatible?
replied to their post 14 days ago
the Orion in Refract Labs? I let HF have you and Refract Labs stuff show up in feed plus notifications if thats what your asking, plus pinging me sends a notification. i havnt tested it yet though because of this sidetrack, and i accidentally broke a few things in my code base so once i get all of that sorted i will def test it
replied to their post 14 days ago
yeah i know, the base model doesnt even support those tokens, but it was a dataset i could remember easily so thats what i did
reacted to their post with 🔥 14 days ago
Post
6216
Hey everyone! I got sidetracked from my main projects and decided to test out the BananaAll app and see if I could make a small model not regress too much during SFT. Here is what happened:
The base model I chose was BananaMind/BananaMind-2.1-Pico-Preview, and the dataset I used was SupraLabs/SupraThink-Dataset-500x
I trained for 5 whole steps using a LoRA adapter.
Results:
A model that scores better on some benchmarks and worse on others, and still lacks most general capabilities.
You can find the model here: Hoglet-33/Hogleto
Credits:
- Thank you to @Banaxi-Tech for the BananaAll app (works perfectly on Windows and CPU)
- GPT-6 Sol for knowing how to merge some confusing files created by the app
- Myself for the idea
- Someone else somewhere who might have contributed to some of my ideas and might in the future
- And readers like you!
The base model I chose was BananaMind/BananaMind-2.1-Pico-Preview, and the dataset I used was SupraLabs/SupraThink-Dataset-500x
I trained for 5 whole steps using a LoRA adapter.
Results:
A model that scores better on some benchmarks and worse on others, and still lacks most general capabilities.
You can find the model here: Hoglet-33/Hogleto
Credits:
- Thank you to @Banaxi-Tech for the BananaAll app (works perfectly on Windows and CPU)
- GPT-6 Sol for knowing how to merge some confusing files created by the app
- Myself for the idea
- Someone else somewhere who might have contributed to some of my ideas and might in the future
- And readers like you!
- 6 replies
posted an update 14 days ago
Post
6216
Hey everyone! I got sidetracked from my main projects and decided to test out the BananaAll app and see if I could make a small model not regress too much during SFT. Here is what happened:
The base model I chose was BananaMind/BananaMind-2.1-Pico-Preview, and the dataset I used was SupraLabs/SupraThink-Dataset-500x
I trained for 5 whole steps using a LoRA adapter.
Results:
A model that scores better on some benchmarks and worse on others, and still lacks most general capabilities.
You can find the model here: Hoglet-33/Hogleto
Credits:
- Thank you to @Banaxi-Tech for the BananaAll app (works perfectly on Windows and CPU)
- GPT-6 Sol for knowing how to merge some confusing files created by the app
- Myself for the idea
- Someone else somewhere who might have contributed to some of my ideas and might in the future
- And readers like you!
The base model I chose was BananaMind/BananaMind-2.1-Pico-Preview, and the dataset I used was SupraLabs/SupraThink-Dataset-500x
I trained for 5 whole steps using a LoRA adapter.
Results:
A model that scores better on some benchmarks and worse on others, and still lacks most general capabilities.
You can find the model here: Hoglet-33/Hogleto
Credits:
- Thank you to @Banaxi-Tech for the BananaAll app (works perfectly on Windows and CPU)
- GPT-6 Sol for knowing how to merge some confusing files created by the app
- Myself for the idea
- Someone else somewhere who might have contributed to some of my ideas and might in the future
- And readers like you!
- 6 replies
replied to Banaxi-Tech's post 14 days ago
This comment has been hidden
replied to harshitkgupta's post 14 days ago
Why not have used Qwen 3 or 3.5?