Ron Wolf's picture

Ron Wolf

ron-wolf

·

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

bartowski/Peach-9B-8k-Roleplay-GGUF

liked a model 3 days ago

ClosedCharacter/Peach-9B-8k-Roleplay

liked a model 3 days ago

google/gemma-2-9b-it

View all activity

Organizations

None yet

ron-wolf's activity

upvoted a collection 8 days ago

D_AU - Source files for GGUF, EXL2, AWQ, GPTQ, HQQ etc etc

Safetensor source files (by David_AU) to use directly and/or create different quants and/or merges. Link to GGUFS/full model card on each. • 76 items • Updated about 1 month ago • 8

upvoted 2 papers 9 days ago

Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

Paper • 2305.02301 • Published May 3, 2023 • 3

Grokking at the Edge of Numerical Stability

Paper • 2501.04697 • Published 22 days ago • 1

upvoted an article 12 days ago

Article

Finally, a Replacement for BERT: Introducing ModernBERT

Dec 19, 2024

• 514

upvoted 2 collections 20 days ago

Mahou

flammen.ai's production model for casual conversation and character roleplay • 24 items • Updated Oct 14, 2024 • 4

Personal Favorites

Recommended models I use often or like for any reason. I recommend reading their cards for more details. • 10 items • Updated Dec 24, 2024 • 63

upvoted 2 papers 24 days ago

Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference

Paper • 2110.03742 • Published Sep 24, 2021 • 4

Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts

Paper • 2210.03885 • Published Oct 8, 2022 • 1

upvoted a collection 24 days ago

RPMax v1 Models

RPMax series of models with higher creativity and reduced repetition for "classic" RP chats. • 16 items • Updated Dec 6, 2024 • 18

upvoted 2 collections about 1 month ago

EVA Gen 0.0

RP/creative writing specialist models, trained on a curated mixture of natural and synthetic data. • 6 items • Updated Dec 29, 2024 • 3

Recommended large models

This collection contains some of the recent models larger than ~25B parameters that should be high quality and reliable • 15 items • Updated Nov 27, 2024 • 15

upvoted an article about 1 month ago

Article

🐺🐦‍⬛ LLM Comparison/Test: 25 SOTA LLMs (including QwQ) through 59 MMLU-Pro CS benchmark runs

By

•

Dec 4, 2024

• 76

upvoted 2 collections about 1 month ago

Current daily driver's & Past favorites.

10 items • Updated 4 days ago • 12

Lumimaid

3 items • Updated Jul 26, 2024 • 18

upvoted an article about 1 month ago

Article

🚨 ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming

By

•

Jun 25, 2024

• 5

upvoted a collection about 1 month ago

LLM-Papers

112 items • Updated 11 days ago • 3

upvoted an article about 1 month ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13, 2024

• 414

upvoted 3 papers about 1 month ago

TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

Paper • 2412.14161 • Published Dec 18, 2024 • 50

Accelerated Preference Optimization for Large Language Model Alignment

Paper • 2410.06293 • Published Oct 8, 2024 • 5

TrustLLM: Trustworthiness in Large Language Models

Paper • 2401.05561 • Published Jan 10, 2024 • 67