🔄 In a Training Loop

Alexandr Kolesnikov

morginalium

6 21

alexkolesnikov08

AI & ML interests

Extremely small language models, LMs for Russian, transformers and non-transformer architectures

Recent Activity

liked a model 8 days ago

tencent/Hy-MT2-1.8B

liked a dataset 8 days ago

empero-ai/MiniMax-M3-150k-Mixed

liked a dataset 8 days ago

empero-ai/hy3-sft-1500x

View all activity

Organizations

None yet

liked a model 8 days ago

tencent/Hy-MT2-1.8B

Translation • 2B • Updated May 26 • 28k • • 1.22k

liked 3 datasets 8 days ago

liked a model 9 days ago

Agnes-AI/Agnes-3.0-Flash

Image-Text-to-Text • 33B • Updated 9 days ago • 2.04k • 244

liked a model 12 days ago

Banaxi-Tech/BananaMind-2.1-Lite-All-Looped-AdamW

Text Generation • 28.4M • Updated 7 days ago • 2.23k • 2

liked 2 models 14 days ago

inclusionAI/Ling-3.0-tiny

Text Generation • 8B • Updated 1 day ago • 21.5k • 480

yandex/AliceAI-T5-35B-A0.6B

35B • Updated 14 days ago • 2.26k • 144

liked 3 models 22 days ago

deepvk/GeRaCl-USER2-base

Zero-Shot Classification • 0.2B • Updated Jun 10, 2025 • 398 • 23

deepvk/USER2-small

nvidia/llama-nemotron-embed-1b-v2

Feature Extraction • 1B • Updated May 20 • 412k • 64

published a bucket 22 days ago

morginalium/embedder-models

0 Bytes

liked a model 23 days ago

KvaytG/rubert-tiny2-toxic-detector

Text Classification • 29.2M • Updated Jul 29 • 64 • 1

liked a dataset 23 days ago

wikimedia/wikipedia

Viewer • Updated Jan 9, 2024 • 61.6M • 275k • 1.55k

updated a model 26 days ago

morginalium/tinystories-tokenizers

Updated 26 days ago

reacted to appvoid's post with 🔥 26 days ago

Post

3304

Love how the small lm community is getting identity over time:

- Channel-Mixing
- XSA
- Three-tower
- Digit aware
- Loops

No one is doing the same! That's so cool.

36 replies

published a model 26 days ago

morginalium/barrie

Updated 26 days ago

liked a model about 1 month ago

ai-sage/Giga-Embeddings-instruct-480M-0826

upvoted a changelog about 1 month ago

Hugging Face Changelog

Granular Feature Access

Aug 12

• 405