BananaMind
🍌
3
Explore small language model experiments and benchmarks
🤏 Small Decision Models soon!
OpenEngineer
Monster-Code
P(doom) Rejects the premise
AI & ML interests
@Lightbend
Recent Activity
liked a Space about 22 hours ago
BananaMind/blog reacted to Banaxi-Tech's post with ➕ about 22 hours ago
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: https://huggingface.co/spaces/BananaMind/blog#bananamind-gate-attention
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!!!!
reacted to Banaxi-Tech's post with 🔥 about 22 hours ago
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: https://huggingface.co/spaces/BananaMind/blog#bananamind-gate-attention
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!!!!
Organizations
liked a
Space about 22 hours ago
reacted to Banaxi-Tech's post with ➕🔥🚀👀❤️😎 about 22 hours ago
Post
2005
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!!!!
- 8 replies
liked a
model about 22 hours ago
liked a
Space about 22 hours ago
reacted to danielhanchen's post with 🧠➕👍🔥❤️ about 23 hours ago
Post
4168
You can now train your own Decision model like Jev locally!
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth
- 4 replies
reacted to SeaWolf-AI's post with 😎🔥👍 1 day ago
Post
3985
🧠 We just released Darwin-27B-ZTC, a judgment engine that reaches a verdict without generating anything.
Most LLMs answer by generating, decoding one token at a time. Darwin-27B-ZTC takes a different route.
⚙️ How it works
🔹 It makes its call in a single forward pass.
🔹 Zero generated tokens, and no decoding loop.
🔹 That keeps latency and cost far below what a generative model needs.
🎯 What it judges
🔹 It handles several question types: free-form correctness (noul), multiple choice (choice), and scoring (score).
🔹 For each one it hands back a calibrated confidence, not just an answer.
📊 How well calibrated (measured)
🔹 KL 0.204, Brier 0.097, so the confidence it reports lines up with what actually happens.
🔹 0.743 accuracy (zero-shot, general split), across 2,000 judgments with zero errors.
🔹 By type: noul 0.847, choice 0.723, score 0.675.
🔹 None of the benchmark's train split went into it. It is pure zero-shot.
🚀 Where it fits
🔹 Grading at scale, model routing, safety gating, anywhere you want a fast decision without paying for generation.
🏆 It currently sits at #1 on the official typed-decisions leaderboard on Hugging Face (0.743 accuracy, zero-shot).
🔗 Links
Model: FINAL-Bench/Darwin-27B-ZTC
Leaderboard: LocalLLaMA/typed-decisions
Curious to hear what you make of the single-pass, no-generation approach. 🙌
Most LLMs answer by generating, decoding one token at a time. Darwin-27B-ZTC takes a different route.
⚙️ How it works
🔹 It makes its call in a single forward pass.
🔹 Zero generated tokens, and no decoding loop.
🔹 That keeps latency and cost far below what a generative model needs.
🎯 What it judges
🔹 It handles several question types: free-form correctness (noul), multiple choice (choice), and scoring (score).
🔹 For each one it hands back a calibrated confidence, not just an answer.
📊 How well calibrated (measured)
🔹 KL 0.204, Brier 0.097, so the confidence it reports lines up with what actually happens.
🔹 0.743 accuracy (zero-shot, general split), across 2,000 judgments with zero errors.
🔹 By type: noul 0.847, choice 0.723, score 0.675.
🔹 None of the benchmark's train split went into it. It is pure zero-shot.
🚀 Where it fits
🔹 Grading at scale, model routing, safety gating, anywhere you want a fast decision without paying for generation.
🏆 It currently sits at #1 on the official typed-decisions leaderboard on Hugging Face (0.743 accuracy, zero-shot).
🔗 Links
Model: FINAL-Bench/Darwin-27B-ZTC
Leaderboard: LocalLLaMA/typed-decisions
Curious to hear what you make of the single-pass, no-generation approach. 🙌
- 2 replies
liked 2
models 1 day ago
upvoted an article 3 days ago
Article
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
nvidia
• • 16