ponzi's picture

ponzi

ponzles

·

AI & ML interests

None yet

Recent Activity

liked a model about 23 hours ago

onnx-community/gemma-4-E2B-it-ONNX

liked a model 1 day ago

scragnog/Ace-Step-1.5-ScragVAE

liked a model 2 days ago

huihui-ai/Huihui4-8B-A4B-GGUF

View all activity

Organizations

None yet

upvoted 2 papers 3 days ago

SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection

Paper • 2509.16060 • Published Sep 19, 2025 • 1

Refusal in Language Models Is Mediated by a Single Direction

Paper • 2406.11717 • Published Jun 17, 2024 • 10

upvoted a changelog 19 days ago

Hugging Face Changelog

Agent Traces on the Hub

20 days ago

• 117

upvoted a collection about 2 months ago

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes. • 42 items • Updated 3 days ago • 41

upvoted an article 2 months ago

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

+4

Feb 20

•

504

upvoted 3 articles 4 months ago

Article

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

+4

Dec 18, 2025

•

124

Article

Shadow AI - Where are the CIOs?

Dec 19, 2025

•

31

Article

Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models

Dec 15, 2025

•

111

upvoted an article 5 months ago

Article

Norm-Preserving Biprojected Abliteration

Nov 6, 2025

•

77

upvoted a collection 5 months ago

The Bestiary

Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated Nov 16, 2025 • 112

upvoted a paper 5 months ago

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published Nov 12, 2025 • 128

upvoted 4 collections 6 months ago

abliterated loras

6 items • Updated Nov 25, 2025 • 1

Cerebras REAP

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 138

Qwen3

Models from the Qwen3 series • 11 items • Updated Nov 3, 2025 • 3

Granite Quantized Models

Quantized versions of IBM Granite models. • 44 items • Updated 6 days ago • 33

upvoted a collection 7 months ago

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 197

upvoted a paper 10 months ago

On Path to Multimodal Generalist: General-Level and General-Bench

Paper • 2505.04620 • Published May 7, 2025 • 83

upvoted 2 collections 10 months ago

ERNIE 4.5

collection of ERNIE 4.5 models. • 27 items • Updated Nov 11, 2025 • 188

BGE

31 items • Updated Feb 4 • 157

upvoted a collection 11 months ago

DeepSeek-R1

10 items • Updated Nov 27, 2025 • 843