Dhruvil Patel

dhruvil237

·

dhruvil237

AI & ML interests

Deep Learning, NLP

Recent Activity

new activity 4 days ago

deepseek-ai/dspark_gemma4_12b_block7:How to use it on vLLM?

new activity 20 days ago

google/gemma-4-12B-it:gemma-4-12B-it: deterministic "thought\n thought\n …" degenerate loop on long agent prompts (~60% reproducer, 4-bit, repros across temperatures)

new activity 3 months ago

dhruvil237/gemma-4-26B-A4B-it-W4A16:Sglang throws an error

View all activity

Organizations

None yet

liked a model 4 months ago

dhruvil237/gemma-4-26B-A4B-it-W4A16

Image-Text-to-Text • 26B • Updated Apr 27 • 20.3k • 3

liked a Space 8 months ago

The Smol Training Playbook

The secrets to building world-class LLMs

liked a Space over 3 years ago

Stable Diffusion Inpainting