SemanticCompression
💬
7
Compress text while preserving meaning
Carlo Moro
cnmoro
AI & ML interests
None yet
Recent Activity
new activity
1 day ago
cnmoro/Qwen2.5-0.5B-Portuguese-v1:Improve language tag
liked
a Space
2 days ago
cnmoro/SemanticCompression
liked
a model
2 days ago
Biatron/biatron-345m
Organizations
Improve language tag
#3 opened 10 months ago
by
lbourdois
liked
a
Space
2 days ago
liked
a
model
2 days ago
liked
a
dataset
2 days ago
liked
a
model
2 days ago
High RAM usage
1
#1 opened 4 days ago
by
cnmoro
reacted to
OzTianlu's
post with 👀
4 days ago
Post
3424
O(1) inference is the foundational design of Spartacus-1B-Instruct 🛡️ !
NoesisLab/Spartacus-1B-Instruct
We have successfully replaced the KV-cache bottleneck inherent in Softmax Attention with Causal Monoid State Compression. By defining the causal history as a monoid recurrence, , the entire prefix is lossily compressed into a fixed-size state matrix per head.
The technical core of this architecture relies on the associativity of the monoid operator:
Training: parallel prefix scan using Triton-accelerated JIT kernels to compute all prefix states simultaneously.
Inference: True sequential updates. Memory and time complexity per token are decoupled from sequence length.
Explicit Causality: We discard RoPE and attention masks. Causality is a first-class citizen, explicitly modeled through learned, content-dependent decay gates.
Current zero-shot benchmarks demonstrate that Spartacus-1B-Instruct (1.3B) is already outperforming established sub-quadratic models like Mamba-1.4B and RWKV-6-1.6B on ARC-Challenge (0.3063). Recent integration of structured Chain-of-Thought (CoT) data has further pushed reasoning accuracy to 75%.
The "Spartacus" era is about scaling intelligence, not the memory wall ♾️.
NoesisLab/Spartacus-1B-Instruct
We have successfully replaced the KV-cache bottleneck inherent in Softmax Attention with Causal Monoid State Compression. By defining the causal history as a monoid recurrence, , the entire prefix is lossily compressed into a fixed-size state matrix per head.
The technical core of this architecture relies on the associativity of the monoid operator:
Training: parallel prefix scan using Triton-accelerated JIT kernels to compute all prefix states simultaneously.
Inference: True sequential updates. Memory and time complexity per token are decoupled from sequence length.
Explicit Causality: We discard RoPE and attention masks. Causality is a first-class citizen, explicitly modeled through learned, content-dependent decay gates.
Current zero-shot benchmarks demonstrate that Spartacus-1B-Instruct (1.3B) is already outperforming established sub-quadratic models like Mamba-1.4B and RWKV-6-1.6B on ARC-Challenge (0.3063). Recent integration of structured Chain-of-Thought (CoT) data has further pushed reasoning accuracy to 75%.
The "Spartacus" era is about scaling intelligence, not the memory wall ♾️.
liked
a
model
4 days ago
liked
a
model
5 days ago
reacted to
AdinaY's
post with 🚀
7 days ago
Post
3002
MiniMax M2.5 is now available on the hub 🚀
MiniMaxAI/MiniMax-M2.5
✨ 229B - Modified MIT license
✨37% faster than M2.1
✨ ~$1/hour at 100 TPS
MiniMaxAI/MiniMax-M2.5
✨ 229B - Modified MIT license
✨37% faster than M2.1
✨ ~$1/hour at 100 TPS
- 2 replies
liked
a
model
10 days ago
upvoted
an
article
10 days ago
Article
LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling
•
44
liked
a
model
14 days ago
liked
a
model
23 days ago
reacted to
Javedalam's
post with 🔥
23 days ago
Post
2970
KittenTTS Nano — Tiny, Expressive, Practical
KittenTTS Nano is a lightweight, CPU-only text-to-speech model designed to prove that natural, expressive voices don’t require massive cloud stacks or GPUs. At roughly ~15M parameters, it runs fast on modest hardware, supports multiple expressive voices, and exposes simple controls for pacing and tone. This makes it ideal for edge devices, demos, and anyone who wants full control over TTS without latency, lock-in, or infrastructure overhead.
Try it here
Javedalam/KittenTTS
The model page
KittenML/kitten-tts-nano-0.2
KittenTTS Nano is a lightweight, CPU-only text-to-speech model designed to prove that natural, expressive voices don’t require massive cloud stacks or GPUs. At roughly ~15M parameters, it runs fast on modest hardware, supports multiple expressive voices, and exposes simple controls for pacing and tone. This makes it ideal for edge devices, demos, and anyone who wants full control over TTS without latency, lock-in, or infrastructure overhead.
Try it here
Javedalam/KittenTTS
The model page
KittenML/kitten-tts-nano-0.2
- 2 replies
liked
a
model
24 days ago
liked
a
model
25 days ago
liked
a
Space
about 1 month ago
updated
a
model
about 1 month ago
Portuguese GGUFs?
2
#1 opened about 1 month ago
by
xande-p