🏗️ 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 and we are enthusiastic about AI. We are based in Australia 🇦🇺

Recent Activity

reacted to smilyai-large-team's post with 🔥 about 9 hours ago

Hey everyone! You can try MiniCoder-1 here. @Bc-AI is still working on the GRPO and DPO but this is a small early beta test space! https://ml-intern-explorers-minicoder-1-inference.hf.space

reacted to smilyai-large-team's post with 👀 about 9 hours ago

Hey everyone! You can try MiniCoder-1 here. @Bc-AI is still working on the GRPO and DPO but this is a small early beta test space! https://ml-intern-explorers-minicoder-1-inference.hf.space

repliedto Banaxi-Tech's post about 10 hours ago

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 model’s 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.

View all activity

Organizations

$Refract AI Labs's profile picture$

reacted to smilyai-large-team's post with 🔥👀 about 9 hours ago

Post

102

Hey everyone! You can try MiniCoder-1 here. @Bc-AI is still working on the GRPO and DPO but this is a small early beta test space! https://ml-intern-explorers-minicoder-1-inference.hf.space

replied to Banaxi-Tech's post about 10 hours ago

I think he means Claude or other stuff

replied to Hoglet-33's post about 12 hours ago

I meant like if it was good or not lol @Hoglet-33

replied to Hoglet-33's post about 12 hours ago

@Hoglet-33 how did you find Orion? Also I recommend the SFT one it is better at both base and SFT

New activity in BananaMind/BananaMind-2.1-Unified about 12 hours ago

BE CAREFUL OF THIS ACCOUNT !

😔 2

#5 opened about 1 month ago by

RexTRO111

reacted to Hoglet-33's post with 🔥 about 13 hours ago

Post

2336

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!

5 replies

replied to Hoglet-33's post about 13 hours ago

@Hoglet-33 nice! I think small models cannot meaningfully learn to perform CoT tho, i once tried a ton of fancy stuff like SFT, GRPO, DPO even a custom tag loss