John Smith's picture

John Smith PRO

John6666

·

John6666cat

AI & ML interests

None yet

Recent Activity

reacted to MoritzLaurer's post with 🔥 about 4 hours ago

🚀 Releasing a new zeroshot-classifier based on ModernBERT! Some key takeaways: - ⚡ Speed & efficiency: It's multiple times faster and uses significantly less memory than DeBERTav3. You can use larger batch sizes and enabling bf16 (instead of fp16) gave me a ~2x speed boost as well - 📉 Performance tradeoff: It performs slightly worse than DeBERTav3 on average across my zeroshot classification task collection - 🧠 Use cases: I recommend using it for scenarios requiring speed and a larger context window (8k). - 💡 What’s next? I’m preparing a newer version trained on better + longer synthetic data to fully leverage the 8k context window and improve upon the training mix of my older zeroshot-v2.0 models. I also hope that there will be a multilingual variant in the future. Great work by https://huggingface.co/answerdotai ! If you’re looking for a high-speed zeroshot classifier, give it a try! 📄 Resources below: 👇 Base model: https://huggingface.co/MoritzLaurer/ModernBERT-base-zeroshot-v2.0 Large model: https://huggingface.co/MoritzLaurer/ModernBERT-large-zeroshot-v2.0 Updated zeroshot collection: https://huggingface.co/collections/MoritzLaurer/zeroshot-classifiers-6548b4ff407bb19ff5c3ad6f ModernBERT collection with paper: https://huggingface.co/collections/answerdotai/modernbert-67627ad707a4acbf33c41deb

updated a collection about 6 hours ago

Spaces for LLM / VLM / NLP

liked a Space about 6 hours ago

Felguk/Felguk-v0

View all activity

Organizations

John6666's activity

upvoted a paper about 6 hours ago

2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining

Paper • 2501.00958 • Published 5 days ago • 82

upvoted a collection about 8 hours ago

Small Reasoning Model

3 items • Updated 1 day ago • 4

upvoted an article about 13 hours ago

Article

Fine-tune SmolLM's on custom synthetic data

By

•

1 day ago

• 10

upvoted a collection 1 day ago

Mirrored mergekit-ready models

Mirrored models tweaked to be more friendly for mergekit. No pickles allowed. • 7 items • Updated 1 day ago • 1

upvoted an article 1 day ago

Article

🐺🐦‍⬛ LLM Comparison/Test: DeepSeek-V3, QVQ-72B-Preview, Falcon3 10B, Llama 3.3 70B, Nemotron 70B in my updated MMLU-Pro CS benchmark

By

•

4 days ago

• 30

upvoted a collection 1 day ago

Base Merges

Original quants of ZXC merged models. • 19 items • Updated Nov 22, 2024 • 1

upvoted an article 1 day ago

Article

Building Effective Agents with Anthropic’s Best Practices and smolagents ❤️

By

•

2 days ago

• 2

upvoted a collection 2 days ago

Deepthink and Reasoning

Best for Deepthink and Reasoning • 12 items • Updated 2 days ago • 12

upvoted a paper 2 days ago

LTX-Video: Realtime Video Latent Diffusion

Paper • 2501.00103 • Published 7 days ago • 35

upvoted a collection 2 days ago

Vietnamese Math Dataset

Vietnamese Math Dataset • 8 items • Updated Oct 30, 2024 • 2

upvoted a collection 3 days ago

x1 Series

A family of x1 models which have a built-in reasoning abilities. • 1 item • Updated 3 days ago • 1

upvoted an article 3 days ago

Article

Fine-tune a SmolLM on domain-specific synthetic data from a LLM

By

•

3 days ago

• 10

upvoted 4 collections 3 days ago

ANIMA: Biomimicry Models

Different chat versions of the ANIMA model • 5 items • Updated Mar 12, 2024 • 1

Nexus Internal Knowledge Map

Various versions of the same models that have been trained on the Internal Knowledge Map dataset using different methods and frameworks • 9 items • Updated Mar 31, 2024 • 1

sd-seer

Experimental models to convert natural language stable diffusion prompts to tags • 2 items • Updated Oct 20, 2024 • 1

bellman

The currently active versions of bellman, the Swedish finetune. This will be updated to only contain the recommended versions. • 4 items • Updated Oct 21, 2024 • 1

upvoted a collection 4 days ago

OdysseyXL

Odyssey Labs' collection of OdysseyXL, A diffusion model designed for hyperrealism. • 6 items • Updated 4 days ago • 2

upvoted 3 collections 5 days ago

Instrumentality-RP-12B-RU

3 items • Updated 7 days ago • 1

NeverendingStory-RP-12B-RU

3 items • Updated 5 days ago • 1

Special

5 items • Updated 3 days ago • 3