Mike Ravkine's picture

Open to Collab

Mike Ravkine PRO

mike-ravkine

·

the-crypt-keeper

AI & ML interests

LLM Research / Development / Evaluation

Recent Activity

posted an update about 17 hours ago

A word of warning that my initial run of 3.6 produced unfavorable results vs 3.5; performance on out-of-distribution and instruction following tasks appears to have collapsed. Potentially a vLLM 0.19 issue here, the original eval was done with their fork of 0.18. I am re-running both with nightly so we have apples to apples and will report back, curious to get to the bottom of this one.

liked a model 6 days ago

MiniMaxAI/MiniMax-M2.7

liked a model 9 days ago

LGAI-EXAONE/EXAONE-4.5-33B

View all activity

Organizations

liked a model 6 days ago

MiniMaxAI/MiniMax-M2.7

Text Generation • 229B • Updated about 22 hours ago • 258k • • 932

liked a model 9 days ago

LGAI-EXAONE/EXAONE-4.5-33B

Image-Text-to-Text • 34B • Updated 3 days ago • 8.67k • 147

liked 2 models 11 days ago

nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16

Text Generation • Updated 28 days ago • 91.7k • 75

nvidia/Nemotron-Cascade-2-30B-A3B

Text Generation • 32B • Updated 8 days ago • 318k • 474

liked a model 15 days ago

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated 8 days ago • 3.78M • • 2.13k

liked a model 16 days ago

Jackrong/Qwopus3.5-9B-v3

Image-Text-to-Text • 10B • Updated 9 days ago • 227k • 80

liked a model 22 days ago

nvidia/gpt-oss-puzzle-88B

Text Generation • 91B • Updated 8 days ago • 20.3k • 90

liked a model 25 days ago

Nanbeige/Nanbeige4-3B-Thinking-2511

Text Generation • 4B • Updated Dec 17, 2025 • 1.28k • 204

liked 6 models about 1 month ago

Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2

Image-Text-to-Text • 10B • Updated 12 days ago • 32.4k • 158

mistralai/Mistral-Small-4-119B-2603

119B • Updated 23 days ago • 81.5k • 356

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8

Text Generation • 124B • Updated 7 days ago • 653k • 232

QuantTrio/Qwen3.5-397B-A17B-AWQ

Image-Text-to-Text • Updated Mar 2 • 22k • 9

LLM360/K2-Think-V2

Text Generation • 73B • Updated Mar 2 • 1.56k • 29

inclusionAI/Ring-flash-2.0

Text Generation • 103B • Updated Oct 23, 2025 • 130 • 101

liked 2 models about 2 months ago

Qwen/Qwen3.5-35B-A3B

Image-Text-to-Text • 36B • Updated Feb 27 • 3.88M • • 1.39k

Nanbeige/Nanbeige4.1-3B

Text Generation • 4B • Updated 24 days ago • 288k • • 1.09k

liked a model 2 months ago

stepfun-ai/Step-3.5-Flash

Text Generation • 199B • Updated Mar 17 • 143k • • 782

liked 3 models 3 months ago

unsloth/GLM-4.7-Flash-FP8-Dynamic

Text Generation • 30B • Updated Jan 26 • 17.7k • 28

ByteDance-Seed/Stable-DiffCoder-8B-Instruct

Text Generation • 8B • Updated 24 days ago • 1.54k • 134

LoganResearch/ARC-Base-8B-Condensed

Text Generation • 8B • Updated Jan 23 • 28 • 4