ijohn free life's picture

ijohn free life

ijohn07

·

john_whickins

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

google/gemma-3-27b-it-qat-q4_0-gguf

upvoted a collection 2 days ago

upvoted a collection 4 days ago

View all activity

Organizations

ijohn07's activity

upvoted a collection 2 days ago

Llama 4

Llama 4 release • 10 items • Updated 2 days ago • 380

upvoted a collection 4 days ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 8 items • Updated 5 days ago • 101

upvoted a paper 12 days ago

HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs

Paper • 2503.02003 • Published Mar 3 • 46

upvoted a paper 14 days ago

LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

Paper • 2407.03168 • Published Jul 3, 2024 • 3

upvoted 3 collections 18 days ago

Qwen 2.5 Coder Llamafiles (<50B)

Llamafiles for the smaller Qwen 2.5 Coder models • 6 items • Updated Feb 25 • 1

Qwen 2.5 Llamafiles (<50B)

Llamafiles for the smaller Qwen 2.5 text only models • 6 items • Updated Feb 25 • 1

Deepseek Distilled Llamafiles (<50B)

Llamafiles for the smaller Deepseek Distilled Models • 5 items • Updated Feb 25 • 2

upvoted a collection 25 days ago

DeepHermes

Preview models of hybrid reasoner Hermes series • 6 items • Updated 25 days ago • 27

upvoted 4 collections 27 days ago

Gemma 3

4 items • Updated 27 days ago • 15

DeepSeek R1 (All Versions)

DeepSeek R1 - the most powerful reasoning open-source model - available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 29 items • Updated 2 days ago • 215

Gemma 3

All versions of Google's new multimodal models in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 29 items • Updated 2 days ago • 48

Gemma 3 Release

17 items • Updated 5 days ago • 313

upvoted a paper about 2 months ago

LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Paper • 2502.07374 • Published Feb 11 • 39

upvoted a collection about 2 months ago

Hibiki fr-en

Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 5 items • Updated Feb 6 • 52

upvoted a collection 2 months ago

DeepSeek-MoE

DeepSeek MoE series • 3 items • Updated Aug 16, 2024 • 13

upvoted an article 2 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.21k

upvoted a paper 2 months ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28 • 119

upvoted an article 2 months ago

Article

Introducing Community Tools on HuggingChat

Sep 16, 2024

• 36

upvoted a collection 2 months ago

Reasoning Datasets

Distilled synthetic Reasoning datasets • 7 items • Updated Feb 2 • 60