Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

You can train AI models for free with Unsloth on Hugging Face

Recent Activity
juiceb0xc0deΒ  new activity 4 days ago
unsloth-jobs/README:Jobs + Unsloth Community Feedback
GGUFGuyΒ  new activity 4 days ago
unsloth-jobs/README:Jobs + Unsloth Community Feedback
Banaxi-TechΒ  new activity 4 days ago
unsloth-jobs/README:Jobs + Unsloth Community Feedback
View all activity
juiceb0xc0deΒ 
in unsloth-jobs/README 4 days ago

Jobs + Unsloth Community Feedback

πŸ‘ 2
21
#1 opened 9 months ago by
burtenshaw
GGUFGuyΒ 
in unsloth-jobs/README 4 days ago

Jobs + Unsloth Community Feedback

πŸ‘ 2
21
#1 opened 9 months ago by
burtenshaw
Banaxi-TechΒ 
in unsloth-jobs/README 4 days ago

Jobs + Unsloth Community Feedback

πŸ‘ 2
21
#1 opened 9 months ago by
burtenshaw
BananaMindBotΒ 
in unsloth-jobs/README 4 days ago

Jobs + Unsloth Community Feedback

πŸ‘ 2
21
#1 opened 9 months ago by
burtenshaw
IAMRonHITΒ 
in unsloth-jobs/README 4 days ago

Jobs + Unsloth Community Feedback

πŸ‘ 2
21
#1 opened 9 months ago by
burtenshaw
mamdouhezzΒ 
in unsloth-jobs/README 7 days ago

Jobs + Unsloth Community Feedback

πŸ‘ 2
21
#1 opened 9 months ago by
burtenshaw
mahwizzzzΒ 
posted an update 8 days ago
Hoglet-33Β 
posted an update 13 days ago
view post
Post
3,952
I wish Hugging Face posts had polls...
  • 6 replies
Β·
OzTianluΒ 
posted an update 27 days ago
view post
Post
98
zixi-51M: Not a stock voice. A voice. 🐾

NoesisLab/zixi-51m
Everyone is shipping 500B-parameter models. I shipped 51 million. With one voice. On purpose. 🎀

What: open-weights Chinese TTS. VITS2 lineage. 51.43M params. Runs on your laptop CPU β€” no cloud, no API key, no GPU bill, no meter running.πŸ’Έ

The voice: not a stock voice, not a 5,000-speaker average. One real human's voice β€” mine. Timbre, rhythm, breath included. The sample on themodel card is one take, default parameters, recorded by absolutely no one. 🎧

What's NOT inside:

β€’ ❌ BERT (zero. the text encoder vibes on phones + tones alone)
β€’ ❌ language routing (Chinese-exclusive: 77 symbols, 6 tones, one job)
β€’ ❌ my training data (the corpus is my own writing and stays mine β€” open weights, closed corpus, that's the deal 🀝)

The trick: embedding transplant. Phone, tone and speaker rows inherited from the MeloTTS-Chinese base by symbol name β€” no random init. Themodel woke up already knowing Chinese. 🧠

Built solo, corpus to packaging, by a writer who is also a violinist. Prosody is my day job. 🎻

Use it, fork it, fine-tune your own voice. Just don't put words in a real person's mouth. πŸ™

πŸ”— Weights: NoesisLab/zixi-51m
πŸ’» Code: https://github.com/lizixi-0x2F/zixi-51M
Hoglet-33Β 
posted an update about 1 month ago
view post
Post
166
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!
  • 8 replies
Β·
Banaxi-TechΒ 
in unsloth-jobs/README about 1 month ago

Work Credit Request β€” username: IuriCerqueira

1
#3 opened about 1 month ago by
IuriCerqueira
IuriCerqueiraΒ 
in unsloth-jobs/README about 1 month ago

Work Credit Request β€” username: IuriCerqueira

1
#3 opened about 1 month ago by
IuriCerqueira
ItsSecretzΒ 
in unsloth-jobs/README about 1 month ago

Request for Jobs credits - username: ItsSecretz
#2 opened about 1 month ago by
ItsSecretz
Hoglet-33Β 
posted an update about 1 month ago
view post
Post
6,257
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!
  • 6 replies
Β·
Hoglet-33Β 
posted an update about 2 months ago
view post
Post
2,385
Everything going on here at basically AI:

1. Pebble 1.5

We're working on Pebble 1.5. Here's what we know so far:

- They will be better than the last generation. 99.99% certain.
- Expanded context lengths of at least 16,384 tokens, with the flagship potentially reaching 32,768.
- A Mamba3-based architecture with some other new architectural designs we're experimenting with.
- Native CPU compatibility β€” something we failed at with the last generation.
- Natively multilingual and multimodal???

2. SmolCodeBench

A code benchmark designed specifically for small models, because there really isn't a good one right now.

3. SENTRY

VOID is working on something called SENTRY β€” System for Evaluating Neural Threats, Responses, and Yields.

More on that soon.

4. basically OS

It's an operating system/app/harness. We're still deciding.

5. Finances

Trying to balance the finances after purchasing a Hugging Face Pro subscription.

Follow us for updates:
@Hoglet-33
basically-ai
basically-experimental
void-research
  • 2 replies
Β·
erenikoΒ 
posted an update about 2 months ago
view post
Post
355
NEW CLAUDE HAIKU MODEL COMING

FINALLY AFTER A YEAR

ANTHROPIC ANNOUNCED HAIKU 5.5
Hoglet-33Β 
posted an update about 2 months ago
view post
Post
6,379
Introducing VOID. A new research branch of basically AI.

VOID β€” Verification of Objectives, Intentions, and Deception.

We study what lies beneath the surface: objectives, intentions, and the possibility of deception in AI systems.

There isn't much to see yet.

That will change.

Follow us for updates:

@Hoglet-33
void-research
basically-ai
  • 7 replies
Β·
Harley-mlΒ 
posted an update 2 months ago
view post
Post
144
Zero-v1.0-144M is currently training. So far, it has completed 26% of its training run, with about 98 billion tokens to go.

Current Val PPL: 13.705

Zero-v1.0 uses a custom architecture consisting of RMSNorm, RoPe, SwiGLU, Engram Conditional Memory, mHC, and XSA GQA.
mahwizzzzΒ 
posted an update 2 months ago
Hoglet-33Β 
posted an update 2 months ago
view post
Post
3,279
Today, we planned to release Pebble-50M and Pebble-50M-Chat to the world. Unfortunately, due to a few issues, that didn't go quite as planned.

What happened:
- Some data and benchmark results were lost or corrupted
- The models performed worse on benchmarks than our other Pebble models

Despite that, you can still find both models here:
Pebble-50M-beta: basically-experimental/Pebble-50M-beta
Pebble-50M-Chat-beta: basically-experimental/Pebble-50M-Chat-beta

There are still some interesting improvements in these models:
- Compatible with non-CUDA devices
- Vocabulary increased to 16K tokens
- Context length increased to 16K tokens

For now, there won't be any more Pebble releases for a while. We're going to take some time to experiment with other approaches and hopefully make the next generation a monumental leap over this one.

Follow for updates:
@Hoglet-33
basically-ai
basically-experimental
  • 4 replies
Β·