HackerTrans
TopNewTrendsCommentsPastAskShowJobs

amram_art

no profile record

Submissions

MiniCPM-V 4.5: GPT-4o Level MLLM for Image and Video Understanding on Your Phone

huggingface.co
2 points·by amram_art·11 mesi fa·0 comments

Ollama Turbo

ollama.com
430 points·by amram_art·11 mesi fa·243 comments

Rules for AI coding assistants working with the Linux kernel codebase

lore.kernel.org
3 points·by amram_art·12 mesi fa·3 comments

Bash+Awk implementation of the gpt2 124M model

github.com
1 points·by amram_art·12 mesi fa·0 comments

comments

amram_art
·7 mesi fa·discuss
The problem is not in the image models rather the training data and its context. "British museum" for MJ is the image source, "British museum" is the setting for Nano Banana.
amram_art
·12 mesi fa·discuss
https://lore.kernel.org/lkml/20250725175358.1989323-2-sashal... part2 https://lore.kernel.org/lkml/20250725175358.1989323-3-sashal... part 3