Vladimir G.'s picture

In a Training Loop 🔄

Vladimir G.

0xA50C1A1

·

0xA50C1A1

AI & ML interests

None yet

Recent Activity

updated a collection about 10 hours ago

updated a collection about 10 hours ago

updated a model about 11 hours ago

0xA50C1A1/Qwen3-4B-Instruct-2507-Heretic

View all activity

Organizations

None yet

upvoted a paper 11 days ago

Ministral 3

Paper • 2601.08584 • Published Jan 13 • 58

upvoted a collection 11 days ago

Archive

A dump of my fine-tuning experiments • 4 items • Updated about 10 hours ago • 2

upvoted 2 collections 17 days ago

Qwen3.5

21 items • Updated 8 days ago • 1.2k

Qwen3.5

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 5 days ago • 114

upvoted a collection 22 days ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 43 items • Updated 15 days ago • 701

upvoted a collection 24 days ago

No breaks on this tractor

Models uncensored using Heretic (MPOA). • 19 items • Updated about 10 hours ago • 1

upvoted an article 26 days ago

Article

Fine-Tuning Phi-4 with Unsloth

May 15, 2025

•

5

upvoted a changelog 29 days ago

Hugging Face Changelog

Scoped Full-text Search

Feb 10

• 89