PromptCraft-Robotics
Community for applying LLMs to robotics and a robot simulator with ChatGPT integration (by microsoft)
mm-cot
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated) (by amazon-science)
PromptCraft-Robotics | mm-cot | |
---|---|---|
4 | 12 | |
1,714 | 3,671 | |
2.3% | 0.4% | |
1.1 | 2.8 | |
3 months ago | about 1 month ago | |
Python | Python | |
MIT License | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
PromptCraft-Robotics
Posts with mentions or reviews of PromptCraft-Robotics.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-03-11.
- Eu entendo como o CHATGPT elabora textos, mas nao entendo como ele é capaz de dizer qual é a resposta certa numa questão de múltipla escolha, nem como ele resolve problemas matemáticos. Alguém poderia explicar ?
-
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
People are already creating sophisticated prompts that are literally engineering problems, so prompting has indeed become a tool of its own.
- ChatGPT for Robotics
mm-cot
Posts with mentions or reviews of mm-cot.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-02-24.
-
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
Sounds like you want multi-modality. People are working on it.
- Multimodal Chain-of-Thought Reasoning in Language Models
-
What. The. ***k. [less than 1B parameter model outperforms GPT 3.5 in science multiple choice questions]
Github: https://github.com/amazon-science/mm-cot
-
ChatGPT competitors: Amazon jumps into fray with generative AI better than GPT-3.5.
Classics GitHub, build is failing: https://github.com/amazon-science/mm-cot/issues/5
-
This is Revolutionary?! Amazon's 738 Million(!!!) parameter's model outpreforms humans on sience, vision, language and much more tasks.
https://github.com/amazon-science/mm-cot seems to have models published but I haven't tried it at all.
-
Is Google Flan-T5 better than OpenAI GPT-3?
There was a paper today that for the related benchmark (ScienceQA) showed massively improved and better than GPT-3 performance with Flan T5 modified to comprehend multi modal images when answering questions that ... often but not always ... contain physical properties to reason about (the most shocking relevation imo is that the accuracy on text-only questions in all subjects improved... not just those focused on physical questions), here's the repo: https://github.com/amazon-science/mm-cot
-
Multimodal Chain-Of-Thought Reasoning In Language Models
There is a GitHub repo: https://github.com/amazon-science/mm-cot
But it doesn't look all that easy to stand up.
-
[R] Multimodal Chain-of-Thought Reasoning in Language Models - Amazon Web Services Zhuosheng Zhang et al - Outperforms GPT-3.5 by 16% (75%->91%) and surpasses human performance on ScienceQA while having less than 1B params!
Fortunately, Pan Lu et al. released the ScienceQA benchmark, just in time. This is a great contribution to the community and we benefited from it by testing our idea early on this benchmark (see acknowledgement in our GitHub repo). Showing the promise of fine-tuning a smaller model with task-specific datasets (rather than feeding in-context learning demos to a larger generalist LLM) is exactly what we wanted (you may feel more motivated after reading the T-Few paper).
-
Multimodal Chain-of-Thought Reasoning in Language Models (New opensource model from Amazon outperforming GPT3.5)
Github (and model weights download links) : https://github.com/amazon-science/mm-cot Paper : https://arxiv.org/pdf/2302.00923.pdf Twitter link : https://twitter.com/arankomatsuzaki/status/1621323705686134788
What are some alternatives?
When comparing PromptCraft-Robotics and mm-cot you can also consider the following projects:
visual-chatgpt - Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models [Moved to: https://github.com/microsoft/TaskMatrix]
FlexGen - Running large language models on a single GPU for throughput-oriented scenarios.