habitat-sim
transformers
Our great sponsors
habitat-sim | transformers | |
---|---|---|
5 | 174 | |
2,351 | 124,557 | |
3.0% | 2.7% | |
8.8 | 10.0 | |
5 days ago | 5 days ago | |
C++ | Python | |
MIT License | Apache License 2.0 |
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.
habitat-sim
-
Break into CV with background in biological vision and neuroscience
Spot on! I think you grasped the general idea. During some of my 3d studies, I collected data about hand movements, eye movements and navigation paths within scenes, which could potentially be used for training data in robots (e.g. to train robot arm-suction grip, visual input and navigation respectively). I see projects like this https://aihabitat.org/, where my research seems quite relevant.
-
Virtual environment frameworks
I need an easy to set up simulation of a 3d environment and I was wondering what you guys are using. Something like https://aihabitat.org/ . It already comes with rich visuals, which is quite important in my case and it works out of the box so I don't need to waste time developing my own models and graphics. Unfortunately habitat ai doesn't work on windows. Are there some alternatives?
- [D] Have we stopped researching agents?
-
[D] Looking for open source projects to contribute
There are plenty of them out there. I spend a lot of time contributing to open source projects like Habitat-Sim https://github.com/facebookresearch/habitat-sim and Habitat-Lab https://github.com/facebookresearch/habitat-lab which have a ton of open issues and code maintaince stuff that we would welcome contributions of.
-
[R] Best drone simulator for ML purposes
With some hacks it is pretty easy to get drones working in Habitat-Sim: https://github.com/facebookresearch/habitat-sim
transformers
-
Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding
The HuggingFace transformers library already has support for a similar method called prompt lookup decoding that uses the existing context to generate an ngram model: https://github.com/huggingface/transformers/issues/27722
I don't think it would be that hard to switch it out for a pretrained ngram model.
-
AI enthusiasm #6 - Finetune any LLM you want๐ก
Most of this tutorial is based on Hugging Face course about Transformers and on Niels Rogge's Transformers tutorials: make sure to check their work and give them a star on GitHub, if you please โค๏ธ
-
Schedule-Free Learning โ A New Way to Train
* Superconvergence + LR range finder + Fast AI's Ranger21 optimizer was the goto optimizer for CNNs, and worked fabulously well, but on transformers, the learning rate range finder sadi 1e-3 was the best, whilst 1e-5 was better. However, the 1 cycle learning rate stuck. https://github.com/huggingface/transformers/issues/16013
-
Gemma doesn't suck anymore โ 8 bug fixes
Thanks! :) I'm pushing them into transformers, pytorch-gemma and collabing with the Gemma team to resolve all the issues :)
The RoPE fix should already be in transformers 4.38.2: https://github.com/huggingface/transformers/pull/29285
My main PR for transformers which fixes most of the issues (some still left): https://github.com/huggingface/transformers/pull/29402
- HuggingFace Transformers: Qwen2
- HuggingFace Transformers Release v4.36: Mixtral, Llava/BakLlava, SeamlessM4T v2
- HuggingFace: Support for the Mixtral Moe
-
Paris-Based Startup and OpenAI Competitor Mistral AI Valued at $2B
If you want to tinker with the architecture Hugging Face has a FOSS implementation in transformers: https://github.com/huggingface/transformers/blob/main/src/tr...
If you want to reproduce the training pipeline, you couldn't do that even if you wanted to because you don't have access to thousands of A100s.
-
Fail to reproduce the same evaluation metrics score during inference.
I am aware that using mixed precision reduces the stability of weight and there will be little consistency but don't expect it to be this much. I have attached the graph of evaluation metrics. If someone can give me some insight into this issue, that would be great.
-
[D] What is a good way to maintain code readability and code quality while scaling up complexity in libraries like Hugging Face?
In transformers, they tried really hard to have a single function or method to deal with both self and cross attention mechanisms, masking, positional and relative encodings, interpolation etc. While it allows a user to use the same function/method for any model, it has led to severe parameter bloat. Just compare the original implementation of llama by FAIR with the implementation by HF to get an idea.
What are some alternatives?
gazebo-classic - Gazebo classic. For the latest version, see https://github.com/gazebosim/gz-sim
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
carla - Open-source simulator for autonomous driving research.
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
bootcamp - Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
llama - Inference code for Llama models
nn - ๐งโ๐ซ 60 Implementations/tutorials of deep learning papers with side-by-side notes ๐; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), ๐ฎ reinforcement learning (ppo, dqn), capsnet, distillation, ... ๐ง
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
docarray - Represent, send, store and search multimodal data
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
habitat-lab - A modular high-level library to train embodied AI agents across a variety of tasks and environments.
huggingface_hub - The official Python client for the Huggingface Hub.