ijohn free life's picture

ijohn free life

ijohn07

·

john_whickins

AI & ML interests

None yet

Recent Activity

liked a Space 1 day ago

ACE-Step/ACE-Step

liked a Space 1 day ago

darkc0de/VoiceChat

liked a model 1 day ago

cognition-ai/Kevin-32B

View all activity

Organizations

ijohn07's activity

upvoted 2 collections 7 days ago

Phi-4

Phi-4 family of small language, multi-modal and reasoning models. • 13 items • Updated 6 days ago • 141

Phi-4 (All Versions)

Microsoft's Phi-4 models including Reasoning + Reasoning Plus & mini. Includes Dynamic 2.0 GGUF, 4-bit & 16-bit versions. Includes Unsloth's bug fixes • 20 items • Updated 6 days ago • 68

upvoted 2 collections 9 days ago

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 65 items • Updated 7 days ago • 137

Qwen3

27 items • Updated about 2 hours ago • 541

upvoted a paper 9 days ago

Gemma 3 Technical Report

Paper • 2503.19786 • Published Mar 25 • 50

upvoted an article 12 days ago

Article

Tiny Agents: a MCP-powered agent in 50 lines of code

13 days ago

• 219

upvoted 2 collections 14 days ago

OLMo 2

Artifacts for the OLMo 2 release. • 35 items • Updated 7 days ago • 119

OpenMathReasoning

Models and datasets from "AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset" • 7 items • Updated 2 days ago • 35

upvoted 3 collections 15 days ago

Other Models

Misc • 2 items • Updated 7 days ago • 1

Amoral Collection - Gemma 3

Unaligned LLMS • 4 items • Updated 7 days ago • 5

Amoral Collection - Gemma 3 QAT

4 items • Updated 7 days ago • 3

upvoted an article 22 days ago

Article

Cohere on Hugging Face Inference Providers 🔥

22 days ago

• 124

upvoted 4 collections 23 days ago

InternVL3

34 items • Updated 18 days ago • 65

Kimina Prover Preview

State-of-the-Art Models for Formal Mathematical Reasoning • 5 items • Updated 10 days ago • 29

Skywork-OR1

Skywork Open Reasoner 1 • 8 items • Updated 25 days ago • 22

GLM-4-0414

GLM-4-0414 series model • 8 items • Updated 23 days ago • 123

upvoted a collection 27 days ago

Kimi-VL-A3B

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 6 items • Updated 26 days ago • 66

upvoted a collection 29 days ago

Cogito v1 Preview

5 items • Updated 30 days ago • 108

upvoted a collection 30 days ago

HiDream-I1

A collections of HiDream-I1 models. • 4 items • Updated 30 days ago • 30

upvoted a collection about 1 month ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 20 days ago • 187