wrapyfi
wrapyfi-examples_llama
wrapyfi | wrapyfi-examples_llama | |
---|---|---|
4 | 2 | |
70 | 128 | |
- | 0.0% | |
9.6 | 4.0 | |
20 days ago | about 1 year ago | |
Python | Python | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 only |
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.
wrapyfi
-
Wrapyfi for distributing LLaMA by Meta on different machines
The authors present an example of combining Wrapyfi (https://github.com/fabawi/wrapyfi), a Python wrapper for message-oriented and robotics middleware, with LLaMA (https://github.com/facebookresearch/llama), a series of large language models from Meta AI. They demonstrate how Wrapyfi can enable running LLaMA on multiple mid-range machines with high inference speed and low cost. They also provide links to their GitHub repository (https://github.com/modular-ml/wrapyfi-examples_llama) and paper (https://arxiv.org/abs/2302.09648) for more details. They state that this example can revolutionize natural language processing tasks such as text generation, summarization, question answering, sentiment analysis, etc. without having to buy new hardware and use their existing infrastructure!
- Wrapify is a middleware communication wrapper for running the same script on multiple machines. Run the Python script everywhere and choose where each method executes by simply declaring it as a publisher or a listener [currently supports YARP; ROS and ROS2 coming soon]
wrapyfi-examples_llama
- [D] Is it possible to run Meta's LLaMA 65B model on consumer-grade hardware?
-
Wrapyfi for distributing LLaMA by Meta on different machines
The authors present an example of combining Wrapyfi (https://github.com/fabawi/wrapyfi), a Python wrapper for message-oriented and robotics middleware, with LLaMA (https://github.com/facebookresearch/llama), a series of large language models from Meta AI. They demonstrate how Wrapyfi can enable running LLaMA on multiple mid-range machines with high inference speed and low cost. They also provide links to their GitHub repository (https://github.com/modular-ml/wrapyfi-examples_llama) and paper (https://arxiv.org/abs/2302.09648) for more details. They state that this example can revolutionize natural language processing tasks such as text generation, summarization, question answering, sentiment analysis, etc. without having to buy new hardware and use their existing infrastructure!
What are some alternatives?
nmea_navsat_driver - ROS package containing drivers for NMEA devices that can output satellite navigation data (e.g. GPS or GLONASS).
llama - Inference code for Llama models
aztarna - aztarna, a footprinting tool for robots.
llama-cpu - Fork of Facebooks LLaMa model to run on CPU
Pyluos - A Python library to program a Luos based network through a high level interface.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
interbotix_ros_toolboxes - Support-level ROS Packages for Interbotix Robots
text-g
evarobot - This repository includes the Evarobot ROS Noetic packages.
llama-int8 - Quantized inference code for LLaMA models
interbotix_ros_manipulators - ROS Packages for Interbotix Arms
linorobot2 - Autonomous mobile robots (2WD, 4WD, Mecanum Drive)