The A.I Megathread (LLM , GPT , Development)
Be Strong Blackman
All Star
Great thread. What are some of your favorite AI releases @op? I like perplexity
I like vicuna, bard and chatgpt(mostly for coding tasks).
Segment Anything in High Quality
Lei Ke, Mingqiao Ye, Martin Danelljan, Yifan Liu, Yu-Wing Tai, Chi-Keung Tang, Fisher YuGitHub - SysCV/sam-hq: Segment Anything in High Quality
Segment Anything in High Quality. Contribute to SysCV/sam-hq development by creating an account on GitHub.
github.com
Segment Anything in High Quality
We propose HQ-SAM to upgrade SAM for high-quality zero-shot segmentation. Refer to our paper for more details. Our code and models will be released in two weeks. Stay tuned!
Visual comparison between SAM and HQ-SAM
SAM vs. HQ-SAM
|
|
|
|
|
|
Abstract Recent research has focused on enhancing the capability of smaller models through imitation learning, drawing on the outputs generated by large foundation models (LFMs). A number of issues impact the quality of these models, ranging from limited imitation signals from shallow LFM outputs; small scale homogeneous training data; and most notably a lack of rigorous evaluation resulting in overestimating the small model’s capability as they tend to learn to imitate the style, but not the reasoning process of LFMs. To address these challenges, we develop Orca, a 13-billion parameter model that learns to imitate the reasoning process of LFMs. Orca learns from rich signals from GPT-4 including explanation traces; step-by-step thought processes; and other complex instructions, guided by teacher assistance from ChatGPT. To promote this progressive learning, we tap into large-scale and diverse imitation data with judicious sampling and selection. Orca surpasses conventional state-of-the-art instruction-tuned models such as Vicuna-13B by more than 100% in complex zero-shot reasoning benchmarks like BigBench Hard (BBH) and 42% on AGIEval. Moreover, Orca reaches parity with ChatGPT on the BBH benchmark and shows competitive performance (4 pts gap with optimized system message) in professional and academic examinations like the SAT, LSAT, GRE, and GMAT, both in zero-shot settings without CoT; while trailing behind GPT-4. Our research indicates that learning from step-by-step explanations, whether these are generated by humans or more advanced AI models, is a promising direction to improve model capabilities and skills.
"We are working with our legal team to publicly release a diff of the model weights in accordance with LLaMA’s release policy to be published at https://aka.ms/orca-lm.
Work in progress."
can't wait
Last edited:
We are so close to this being ubiquitous. I am looking forward to being able to run my e-library of pdfs and stuff into whatever model comes out in a couple years. Being able to put together the information ive not had the time, or dedication, to read will be amazing!can't wait
if they could achieve those results with a 13 billion parameter model, imagine what a 33B or 65B model could do?
