🤝 Open to Collab

R PRO

juiceb0xc0de

56 31 183

https://github.com/JuiceB0xC0de

AI & ML interests

Mechanistic interpretation SAE weight training Novel architecture exploration Brain atlas builds

Recent Activity

liked a dataset about 11 hours ago

EleutherAI/hack-ignition-benchmark

posted an update about 12 hours ago

🍻Ayy! Think your model has the banter to take on the bartender? Put it to the test in my new space Bellarena! 🍻 1. Choose a .gguf model 2. Watch the showdown Bella is behind the bar at FP16 precision, 8B parameters. I curated a dataset of nothing but absurdist questions. Both models answer a randomly selected draw from 1 to 15, and our regular old house model, Ternary Bonsai 27B👴, judges whether the bartender or the patron brought more entertainment to the bar that evening. I encourage you to please ask bella to contribute to the swear jar while she’s on shift. https://huggingface.co/spaces/juiceb0xc0de/bellarena https://huggingface.co/spaces/juiceb0xc0de/bella-chat

updated a Space about 18 hours ago

juiceb0xc0de/lr-scheduler-benchmark

View all activity

Organizations

posted an update about 12 hours ago

Post

🍻Ayy! Think your model has the banter to take on the bartender? Put it to the test in my new space Bellarena! 🍻
1. Choose a .gguf model
2. Watch the showdown
Bella is behind the bar at FP16 precision, 8B parameters.

I curated a dataset of nothing but absurdist questions. Both models answer a randomly selected draw from 1 to 15, and our regular old house model, Ternary Bonsai 27B👴, judges whether the bartender or the patron brought more entertainment to the bar that evening.

I encourage you to please ask bella to contribute to the swear jar while she’s on shift.

juiceb0xc0de/bellarena
juiceb0xc0de/bella-chat

reacted to danielhanchen's post with 🚀 2 days ago

Post

3689

Qwen3.8-27B Unsloth GGUF is now the #1 most-liked GGUF of all time! 🤗🦥

The model hit 10M downloads and 3.7K likes in just 24 days on Hugging Face - all thanks to you.

GGUF: unsloth/Qwen3.8-27B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.8

5 replies

reacted to nwaughachukwuma's post with 🧠 2 days ago

Post

3165

It’s easy to get distracted by benchmarks, throughput (tok/s), and all the hype around frontier model releases.

This is Shiny Model Syndrome, which makes engineers and teams forget the basic physics of production software, i.e., using the right tool for the job and optimizing for ease of integration.

- Teams spend huge amounts of money on frontier models for document parsing, OCR, detection, segmentation, and other task-specific visual AI workflows.

- Inference marketplaces don’t find it profitable to list task-specific models like glm-ocr, paddleocr, or dots.mocr, even though they’re all superior to frontier VLMs for document parsing and OCR.

- Engineers stitch together multiple endpoints for different use cases across the long tail of visual AI. Those who choose to self-host instead deal with painful infrastructure and GPU ops.

At VLM Run, we wanted one place to run OCR models, VLMs, and ViTs that we could confidently use for our own internal agents and evals. The gateway was born out of that need, and we’ve since opened it to the public.

The gateway exposes a single OpenAI-compatible endpoint for the long tail of visual AI across OCR, document parsing, VQA, detection, segmentation, embeddings, and transcription. Simply point the base_url of your OpenAI SDK at gateway.vlm.run/v1/openai, or ask your agent to connect via MCP (gateway.vlm.run/mcp).

You can swap the model name to compare glm-ocr, dots.mocr, paddleocr-vl-1.6, qwen3.8-27b, gemma4-26b-a4b, and more. We handle serving, runtime, and pipelining behind the scenes to give you high-quality visual intelligence.

- https://vlm.run/gateway
- https://huggingface.co/blog/vlm-run/introducing-gateway
- https://www.vlm.run/blog/introducing-gateway

reacted to their post with 🔥 2 days ago

Post

2920

Dude, Where's My Update? I'll tell you where! ~97.6% of my BF16 parameter coordinates didn't move at all, and the ones that did overshot by ~1.33x.

It's nice to do research that doesn't end in disproving yourself once again and moving on to the next subject once in awhile.

Back to the topic, if you've ever wondered why most of your weights are basically ghosting you nearly every step when you store your weights at bf16, Dude, I Measured It.

https://huggingface.co/blog/juiceb0xc0de/intended-and-realized-updates-in-bf16-fine-tuning#dude-wheres-my-update

reacted to Bc-AI's post with 🔥 2 days ago

Post

2571

Hello everyone!
I have 2 announcements today!
The first one is the launch of our new API platform! You can make a account and get 5 dollars free credits. No credits card needed because i have no idea how to set up a payment's thing. If you want more credits just email me at smilyai@outlook.com .
The platform currently features G1-Preview a preview of G1 and the older Mira-1-Large.
2nd announcement is we have started working on G1-MINI so expect a late October Ish launch
- Bc-AI on behalf of Smilyai-Labs

2 replies

reacted to GoktugD's post with 🤗 2 days ago

Post

2341

🇹🇷 One of our small Turkish models quietly reached **500+ monthly downloads** on Hugging Face.

**Werea-TR-TextRestore — only 300M parameters.**

Its job is simple:

istanbulda hava cok guzel
→ İstanbul'da hava çok güzel.

A lightweight model for restoring Turkish text:
• diacritics
• punctuation
• casing
• corrupted text

**96.5% word accuracy** on real Turkish news sentences.

And it runs without sending your text to a cloud API.

🤗 Try the model:
Werea-co/Werea-TR-TextRestore

🇹🇷 Built in Türkiye. Open source.

If you're working on Turkish NLP, I'd love to hear what we should build next.

#TurkishNLP #HuggingFace #OpenSourceAI #NLP

2 replies

posted an update 3 days ago

Post

2920

reacted to darkc0de's post with 🚀 4 days ago

Post

3217

Big shoutout to Abliterlitics.

These benchmark writeups are consistently some of the most thoughtful, detailed, and genuinely useful posts I read on open-weight model behavior and abliteration. The latest Qwen3.8-27B comparison is another great one.

I look forward to pretty much every post he puts out on the subject. If you're interested in uncensoring, abliteration, model behavior, or comparing techniques across models, definitely check his work out:

https://abliterlitics.dev

replied to Bc-AI's post 6 days ago

The value of thrift my friend. Make your $30 modal credits free every month count. You have a network. $30 x n represented by associates working on the project adds up H100 bucks prettttyyy damn fast. And if you have a sibling a parent or guardian well you do the math. $30 / $3.95 an hour 🥸

replied to Bc-AI's post 6 days ago

You made it this far in what? 2 months since you announced smilyai labs? You'll figure it out. There's plenty of people who take longer trimming datasets for 3b models than you've been operational launching models. Not bad. Also a few weeks ago your time estimate was slashed when you configured a custom triton kernel over lunch hour.

I'll take a look at the model!

replied to Bc-AI's post 6 days ago

Respect. Puttin the Grind in GPU. It's a lifestyle.

reacted to Bc-AI's post with 😔 6 days ago

Post

105

SmilyAI Weekly Update

Hello everyone,

I have some unfortunate news to share with everyone. My earlier estimate for the launch of G1 in late October was inaccurate. We sincerely apologise for any inconvenience this may cause, but with our current compute resources, pretraining a 20B MoE model is not realistically possible within two months.

G1-MINI will also be postponed, but not for nearly as long — only by a few extra months.

This is disappointing, as I know I was excited to launch G1, and I know many people were also watching the model and looking forward to it.

However in my view, I would rather be honest about our limitations than be overly optimistic about something we currently cannot guarantee.

G1 is not cancelled but uh it will be postponed indefinitely until I have the resources needed to train it. This could be next month, or it could take years. For now, I don't want to give another estimated launch date until I know we have the resources to actually make it happen.

In the meantime, SmilyAI will continue developing AI and experimenting with new ideas, and we will provide updates as we go.

Thank you for sticking with us and supporting SmilyAI. We will continue working towards better models in the future.

Also, if you do have the hardware, to run it aka 8xH200s or better, my codebase is fully open under my very permissive license: i-have-no-idea-just-use-this. Basically, do whatever just mention me. Bc-AI/train-g1

— Bc-AI, on behalf of SmilyAI-Labs

10 replies

replied to Bc-AI's post 7 days ago

Oh my we're playing it a little loose and fast with that "mini" adjective aren't we. Here I was expecting something I could run an atlas on 🫤

replied to their post 7 days ago

Thank you I appreciate it.

reacted to Banaxi-Tech's post with 😎 8 days ago

Post

2997

We're going to release our BananaMind 2.1 models very soon!
We're also announcing 2 new models.

All of our models we will train are:
BananaMind 2.1 Flash Lite, 10M parameters with 8M in transformer and 2M in n-gram. 50B pretraining tokens.
BananaMind 2.1 Lite with 25M parameters, 5M in n-gram and 20M in transformer. 75B pretraining tokens.
BananaMind 2.1 Flash with 50M parameters, with undecided n-gram count yet. 100B pretraining tokens.
BananaMind 2.1 Pro with 145M parameters, with undecided n-gram count yet. 150-200B pretraining tokens.
BananaMind 2.1 Coder with 149M parameters with undecided n-gram count yet.
We're now announcing BananaMind 2.1 NanoCoder, a 10M parameter model focused specifically on coding and BananaMind 2.1 MiniCoder which is a 25M parameter model focused on coding.

Follow us:

BananaMind
@Banaxi-Tech
@vovaRL
@DedeProGames

bananamind-research-community

5 replies

replied to their post 8 days ago

Dropping soon! Embedded:

Kernel data
Docker Images
MCP Servers
Buckets
Niche collections

New tools:

Search exclisions
Parameter sliders
Layer digest similarity
Copy-to-run
Verified only toggle

posted an update 9 days ago

Post

3425

Hey I've updated my Hugging Face text generation model search space B-Sides. I always wanted more from HF's model search, so I built one.

I went deeper than the model card, embedding the relevant .json and .py files so you can search for models with custom kernels or exotic imports and specific architecture shapes. You can narrow it down to quantization types and training stacks. If you want to search it and it's not available just make a community post and I would gladly make each query more detailed with an update.

So far over 428,440 text generation models are catalogued with more coming weekly.

On deck: Docker images

https://huggingface.co/spaces/juiceb0xc0de/b-sides

4 replies

reacted to Bc-AI's post with 😎 10 days ago

Post

2528

Building a 6.58B sparse MoE model from scratch on a single GPU.
Hey everyone! Today is day 1 of training Smilyai-Lab's new model I call G1-MINI. It's basically the smaller version of our planned model G1 which will be 20B and activate about 2B per token. MINI activates about 1.16B params per token and is currently training right now. If no errors spring up now, I'd say i can launch sometime around September 15th~ish. Thanks to our beta testers:
@guardamarcos
@ProCreations
@juiceb0xc0de
@Timmy6767
@Sbui503
@atom77777
@Fishtiks
@smartdigitalnetworks
@EmetTheGolum
@smilyai-large-team
@MUK-IS-GOAT
@Bc-AI
@Banaxi-Tech
@vovaRL
@Datdanboi25

9 replies

reacted to Bc-AI's post with 😎 14 days ago

Post

2604

Smilyai News
Hello everyone! August has been a crazy month for us at Smilyai-Labs. We've been doing lots behind the scenes, so here's the latest 👇

1. MiniCoder
We are very close to releasing MiniCoder-1, our first-generation coding model designed for reasoning and coding. Our planned context window is 128K, but the earlier versions probably will not support that long! It's currently in the final stages of DPO so expect a release in early september.
Release: VERY SOON™🤣

2. Smilyai G1
So, the current plan is 20B parameter model total, with a MoE architecture, activating around 2B parameters per token. Its desgigned for maximum performance but keeping it runnable on consumer hardware. It's only a plan and i have no idea when me and the team can finish it. Expect a launch around the end of september to early october-ish. I have no guarantees so don't quote me on the launch date.

3. T1
Smilyai-T1 is another major model we are working on.
The goal for T1 is to take what we learnt from the countless architectural experiments and creating a powerful model designed for thinking. Think MiniCoder but reasons more and G1 but more capable. Its main goals are coding, math, reasoning and general capability.
4. Omni
We are also planning Omni, our first from scratch multimodal model. It will not launch this year as it will take a while. We are actively researching the best architecture for it and we will update progress as we go!

Thanks to our beta testers:
@guardamarcos
@ProCreations
@juiceb0xc0de
@Timmy6767
@Sbui503
@atom77777
@Fishtiks
@smartdigitalnetworks
@EmetTheGolum
@smilyai-large-team
@MUK-IS-GOAT
@Bc-AI

Thanks to my friends who work with me at lunchtimes (Smilyai-Labs team):
@MUK-IS-GOAT
@smilyai-large-team

August was wild. Let’s see what September brings. 🚀

— Bc-AI, on behalf of SmilyAI Labs

reacted to Banaxi-Tech's post with 😎 15 days ago

Post

2875

We’re excited to release BananaMind OS 2.0, a major update to our portable operating system for running AI models locally.

BananaMind OS runs directly from an ISO without Linux, installation, a cloud connection, or modifying your disks.

The new Version 2.0 adds a graphical interface with mouse support, a model library, multi-turn chat, configurable KV cache, maximum tokens and temperature
controls, automatic x87/SSE/SSE2 CPU detection, BIOS support, native UEFI support and a dedicated 486 compatibility mode.

Model weights are not loaded during GRUB or startup. Only the model catalog is read, and the selected model is loaded after BananaMind OS starts.

We now have a new .litemodel format supports multiple architectures, including BananaMind models, SmolLM, SmolLM2, GPT-X2.5, min-spark 1.1 and Rose-Mini.
Check it out at:
https://github.com/BananaMind/BananaMindOS

You can build an ISO yourself using the .sh or .bat script. Select the models and quantizations you want, and the builder will download, quantize
and package them locally.
Prebuilt 10MB, 25MB, 100MB and 250MB model presets are available here:
https://github.com/BananaMind/BananaMindOS/releases/tag/v2.0.0
Use the regular preset ISOs for BIOS and GRUB, including the 486 compatibility mode.

Warning: Im currently uploading the ISOs, all up to 100MB is present, 250MB is getting uploaded
Use the files ending in -uefi.iso for the native x86-64 UEFI graphical frontend and improved firmware mouse support.

The preset name describes the RAM class of the individual included models. Models remain on the ISO until selected, so including multiple models does not load all of them into RAM.
486DX with an x87 FPU, Pentium and newer x86 processors are supported. Modern x86-64 computers are supported through UEFI. It currently doesent support processors without an FPU.

Comment if you want me to run it on 0.04MHz (pls dont)

Video Credit:
Song: Matzan - Redesigned
Music provided by NoCopyrightSounds

3 replies

R PRO

AI & ML interests

Recent Activity

Organizations

juiceb0xc0de's activity