Benhao Tang PRO

benhaotang

AI & ML interests

Physics Master student in theoretical particle physics at Universität Heidelberg, actively looking into the possibilities of integrating AI into future physics research.

Recent Activity

reacted to mitkox's post with 👍 about 2 hours ago

llama.cpp is 26.8% faster than ollama. I have upgraded both, and using the same settings, I am running the same DeepSeek R1 Distill 1.5B on the same hardware. It's an Apples to Apples comparison. Total duration: llama.cpp 6.85 sec <- 26.8% faster ollama 8.69 sec Breakdown by phase: Model loading llama.cpp 241 ms <- 2x faster ollama 553 ms Prompt processing llama.cpp 416.04 tokens/s with an eval time 45.67 ms <- 10x faster ollama 42.17 tokens/s with an eval time of 498 ms Token generation llama.cpp 137.79 tokens/s with an eval time 6.62 sec <- 13% faster ollama 122.07 tokens/s with an eval time 7.64 sec llama.cpp is LLM inference in C/C++; ollama adds abstraction layers and marketing. Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.

reacted to sometimesanotion's post with 🔥 1 day ago

I've managed a #1 score of 41.22% average for 14B parameter models on the Open LLM Leaderboard. As of this writing, sometimesanotion/Lamarck-14B-v0.7 is #8 for all models up to 70B parameters. It took a custom toolchain around Arcee AI's mergekit to manage the complex merges, gradients, and LoRAs required to make this happen. I really like seeing features of many quality finetunes in one solid generalist model.

liked a model 3 days ago

Lyte/Titans-MAC-test

View all activity

Organizations

None yet

spaces 2

Running on Zero

💬

Try Out phi4-qwq-sky-t1

Sleeping

💬

Try out Mistral-Small-Physics

models 10

datasets

None public yet