Evi1ran's picture

Evi1ran

Evi1ran

·

Evilran

AI & ML interests

None yet

Recent Activity

liked a dataset about 20 hours ago

nohurry/Opus-4.6-Reasoning-3000x-filtered

liked a dataset about 20 hours ago

lambda/hermes-agent-reasoning-traces

liked a model about 21 hours ago

dealignai/Gemma-4-31B-JANG_4M-CRACK

View all activity

Organizations

None yet

upvoted an article 3 months ago

Article

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

Oct 23, 2025

•

73

upvoted a paper 3 months ago

3D-MolT5: Towards Unified 3D Molecule-Text Modeling with 3D Molecular Tokenization

Paper • 2406.05797 • Published Jun 9, 2024 • 3

upvoted a collection 4 months ago

NemoGuard

Essential datasets and models for content safety, topic-following, and security guardrails • 13 items • Updated 2 days ago • 21

upvoted an article 5 months ago

Article

🔢 INT4 vs FP4: The Future of 4-Bit Quantization

Nov 19, 2025

•

5

upvoted a paper 6 months ago

MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition

Paper • 2509.19817 • Published Sep 24, 2025 • 1

upvoted a collection 8 months ago

DeepSeek-V3.1

3 items • Updated Mar 2 • 261

upvoted a collection 10 months ago

Higher Precision GGUFs / Imatrix Plus

Models compressed in higher precision with parts of the model compression remaining in F16/full precision. Increases overall quality in all tasks. • 36 items • Updated Mar 4 • 10

upvoted 2 collections 11 months ago

Healthcare LLMs (Aloe family)

Aloe is a family of open fine-tuned Healthcare LLMs trained by HPAI at BSC. See Beta for the 2nd version, either small or big, based on Llama or Qwen. • 8 items • Updated Jul 23, 2025 • 11

ONNX-converted models

Models converted to ONNX for faster CPU inference on LLM Guard. • 20 items • Updated Mar 2 • 2

upvoted an article 11 months ago

Article

Merge Large Language Models with mergekit

Jan 9, 2024

•

154

upvoted 4 collections over 1 year ago

Off Topic Guardrail 🛡️

Fast, lightweight zero-shot classifiers for user prompt's relevance to the system prompt. • 5 items • Updated Jul 28, 2025 • 4

Medical LLMs

LLMs to help you develop an initial understanding of your symptoms before a clinical visit • 9 items • Updated Mar 2 • 3

MedCT

The world's first clinical terminology for non-English society, i.e., Chinese. • 5 items • Updated Mar 2 • 3

Industry Instruction

多语种多行业指令数据集 • 22 items • Updated Feb 4 • 4