Downloads · 30 days
3
8% of all-time downloads
ULTRON-Core-512M-Instruct
HR26kk/ULTRON-Core-512M-Instruct
ULTRON-Core-512M-Instruct is a machine learning model from HR26kk. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
ULTRON-Core-512M-Instruct is an aligned foundation model pre-trained across 81.9 Million total tokens (including 16.4M educational textbook tokens from cosmopedia-100k) and aligned via Supervised Fine-Tuning with Chai…
All-time downloads
40
Public
Parameters
562M
2.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- ultron_core_instruct
- Access
- Public
- Created
- Aug 25, 2026
- Updated
- Sep 4, 2026
- SHA
- 9cd914a3
Model card
From the Hugging Face model README
ULTRON-Core-512M-Instruct (Knowledge Enhanced)
ULTRON-Core-512M-Instruct is an aligned foundation model pre-trained across 81.9 Million total tokens (including 16.4M educational textbook tokens from cosmopedia-100k) and aligned via Supervised Fine-Tuning with Chain-of-Thought (<think>) reasoning.
Specifications
- Base Parameters: 562,382,848 (~512.05M Non-Embedding)
- Architecture: Multi-Head Latent Attention (MLA: $d_c=512, d_R=64$) + QK-LayerNorm
- Vocabulary: 24,576 (Pure-Python Byte-Level BPE, NFC Standard)
- Pre-Training Volume: 81,920,000 clean tokens
- Final SFT Loss: 2.6711
- Type
- ultron_core_instruct
- License
- apache-2.0
- Languages
- en, hi, multilingual
- Created
- Aug 25, 2026
- Updated
- Sep 4, 2026