Jon Doe's picture

Jon Doe

bullpoint

·

AI & ML interests

None yet

Recent Activity

new activity 19 days ago

Qwen/Qwen3.5-397B-A17B:Qwen3.6 397b

new activity 25 days ago

moonshotai/Kimi-K2.6:Fast tokenizer token-ID parity with previous slow tokenizer?

liked a model about 1 month ago

lightseekorg/kimi-k2.6-eagle3-mla

View all activity

Organizations

None yet

upvoted a collection 3 months ago

Qwen3.5

21 items • Updated Mar 9 • 1.67k

upvoted an article 10 months ago

Article

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

kuotient

•

Aug 9, 2025

• 58

upvoted 2 collections over 1 year ago

DeepSeek R1 (All Versions)

DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 37 items • Updated about 15 hours ago • 268

Llama-3.1-Nemotron-70B

SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. • 6 items • Updated 2 days ago • 156