Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
1
2
318
Jack Voide
Mindweller
Follow
gaytri1111's profile picture
21world's profile picture
Arunsajeevan199303's profile picture
7 followers
·
168 following
AI & ML interests
None yet
Recent Activity
liked
a model
about 6 hours ago
OpenMOSS-Team/MOSS-Audio-8B-Thinking
reacted
to
omarkamali
's
post
with 👍
about 21 hours ago
We got Qwen 3.5 to count Rs in Strawberry correctly! 🚨 Building on Sawtone, we’ve been testing a different way to feed language into an LLM to build the next generation of multilingual AI. The usual setup gives the model tokenized text and asks it to perform various linguistic tasks. That works surprisingly well, until it doesn’t. Accents disappear. Words get mangled. Internal structure gets blurred away. And the cost of that gets higher once you move into multilingual and lower-resource settings. So we tried adding a second path. In addition to the normal text input, the model also receives Sawtone: a byte-level word representation that preserves how a word is written, how it sounds, and how it is structured. Same LLM. Better interface. In this proof of concept with Qwen 3.5 0.8B, that pushed our eval from 64% to 88%. The gains showed up exactly where tokenized models usually get shaky: diacritics, character order, exact spelling, and other form-sensitive behavior. Sawtone itself is tokenizer-free, byte-level, and pre-trained across 507 languages. Still early, but promising!
liked
a model
2 days ago
openbmb/VoxCPM2
View all activity
Organizations
None yet
Mindweller
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
about 6 hours ago
OpenMOSS-Team/MOSS-Audio-8B-Thinking
Audio-Text-to-Text
•
9B
•
Updated
about 12 hours ago
•
105
•
23
liked
3 models
2 days ago
openbmb/VoxCPM2
Text-to-Speech
•
Updated
6 days ago
•
10.9k
•
855
FINAL-Bench/Darwin-4B-Genesis
Text Generation
•
8B
•
Updated
4 days ago
•
449
•
6
FINAL-Bench/Darwin-4B-David
Text Generation
•
Updated
4 days ago
•
854
•
21
liked
a Space
2 days ago
Running
on
Zero
MCP
Featured
46
Auffusion
😻
46
Audio Gen, Audio Style Transfer and Audio InPainting
liked
2 models
2 days ago
Intel/gemma-4-31B-it-int4-AutoRound
6B
•
Updated
3 days ago
•
12.4k
•
36
Zigeng/DMax-Coder-16B
Text Generation
•
16B
•
Updated
4 days ago
•
842
•
31
liked
a model
3 days ago
Intel/gemma-4-26B-A4B-it-int4-mixed-AutoRound
5B
•
Updated
11 days ago
•
14.6k
•
11
liked
5 models
5 days ago
UnstableLlama/Qwen3.5-27B-ultra-uncensored-heretic-v2-exl3-8.00bpw
15B
•
Updated
5 days ago
•
42
•
1
AIDC-AI/Marco-Mini-Instruct
Text Generation
•
17B
•
Updated
5 days ago
•
798
•
34
AIDC-AI/Marco-Mini-Base
Text Generation
•
17B
•
Updated
11 days ago
•
496
•
4
AIDC-AI/Marco-Nano-Instruct
Text Generation
•
8B
•
Updated
2 days ago
•
1.75k
•
28
zai-org/GLM-5.1
Text Generation
•
754B
•
Updated
2 days ago
•
84.8k
•
•
1.18k
liked
2 models
6 days ago
qualcomm/Zipformer
Automatic Speech Recognition
•
Updated
5 days ago
•
2
dealignai/Gemma-4-31B-JANG_4M-CRACK
Image-Text-to-Text
•
6B
•
Updated
4 days ago
•
117k
•
1.08k
liked
a model
7 days ago
ACE-Step/acestep-v15-xl-turbo
Text-to-Audio
•
5B
•
Updated
7 days ago
•
3.52k
•
100
liked
a model
8 days ago
k2-fsa/OmniVoice
Text-to-Speech
•
Updated
1 day ago
•
531k
•
556
liked
a model
9 days ago
AlekseyCalvin/Lyrical_ru2en_Gemma4_SFT_3960
Text Generation
•
8B
•
Updated
9 days ago
•
23
•
1
liked
2 models
10 days ago
Aratako/gemma-4-E4B-it-audio-encoder
Feature Extraction
•
Updated
11 days ago
•
511
•
14
Qwen/Qwen3-Embedding-0.6B
Feature Extraction
•
0.6B
•
Updated
Jun 20, 2025
•
6.07M
•
•
977
Load more