DeathGodlike

DeathGodlike's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 20 days ago

Qwen3.6

Collection

15 items • Updated 7 days ago • 40

upvoted 2 collections 23 days ago

Magistry

Collection

Q1 2026 merges based on Mistral 24B • 2 items • Updated Mar 22 • 2

ERNIE-Image

Collection

The serieas of image generation models, including text2img、img2img. • 2 items • Updated 28 days ago • 23

upvoted 3 collections about 1 month ago

Gemma 4

Collection

12 items • Updated 7 days ago • 790

Gemma 4

Collection

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 20 days ago • 177

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Collection

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 120 items • Updated about 18 hours ago • 76

upvoted 2 collections about 2 months ago

heretic-models

Collection

Madness and heresy • 69 items • Updated 4 days ago • 12

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled-v2

Collection

15 items • Updated 5 days ago • 101

upvoted a paper 2 months ago

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

Paper • 2511.10645 • Published Nov 13, 2025 • 10

upvoted 4 collections 2 months ago

ParoQuant

Collection

Pairwise Rotation Quantization for Efficient Reasoning LLM Inference • 20 items • Updated 7 days ago • 25

Qwen 3.5 - Opus Distills

Collection

2 items • Updated Mar 6 • 3

Eagle

Collection

Eagle is a family of frontier vision-language models with data-centric strategies. The model supports both HD image and long-context video input. • 16 items • Updated 3 days ago • 41

Qwen3.5

Collection

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 20 days ago • 152

upvoted an article 3 months ago

view article

Article

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

• 
• 
• +4

ggerganov, ngxson, allozaur, lysandre, victor, julien-c

•

Feb 20

• 505

upvoted a paper 3 months ago

MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration

Paper • 2602.01734 • Published Feb 2 • 32

upvoted 5 collections 3 months ago

DeepSeek-OCR

Collection

2 items • Updated Feb 2 • 31

OCR

Collection

10 items • Updated Feb 4 • 2

DFloat11 | FLUX.1

Collection

Losslessly compressed FLUX.1: requires < 20GB VRAM to run. • 6 items • Updated Jul 5, 2025 • 2

DFloat11 | Gemma 3

Collection

Losslessly Compressed Gemma 3 • 3 items • Updated Jul 5, 2025 • 1

DFloat11 | Qwen 3

Collection

Losslessly compressed Qwen 3 • 4 items • Updated Jul 5, 2025 • 2