wrapyfi-examples_llama
wrapyfi
wrapyfi-examples_llama | wrapyfi | |
---|---|---|
2 | 4 | |
128 | 70 | |
0.0% | - | |
4.0 | 9.6 | |
about 1 year ago | 17 days ago | |
Python | Python | |
GNU General Public License v3.0 only | GNU General Public License v3.0 or later |
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-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!
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]
What are some alternatives?
llama - Inference code for Llama models
nmea_navsat_driver - ROS package containing drivers for NMEA devices that can output satellite navigation data (e.g. GPS or GLONASS).
llama-cpu - Fork of Facebooks LLaMa model to run on CPU
aztarna - aztarna, a footprinting tool for robots.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Pyluos - A Python library to program a Luos based network through a high level interface.
text-g
interbotix_ros_toolboxes - Support-level ROS Packages for Interbotix Robots
llama-int8 - Quantized inference code for LLaMA models
evarobot - This repository includes the Evarobot ROS Noetic packages.
interbotix_ros_manipulators - ROS Packages for Interbotix Arms
linorobot2 - Autonomous mobile robots (2WD, 4WD, Mecanum Drive)