Our great sponsors
-
gpt-neo
Discontinued An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
You can use the codebase EleutherAI created, and download the model from their official release (linked in the readme)
Well, many models hosted on Hugging Face were actually developed without HF Transformers first (and then were ported to HF Transformers by the community). It is the case with GPT-J. Here is the original GPT-J implementation: https://github.com/kingoflolz/mesh-transformer-jax
NOTE:
The number of mentions on this list indicates mentions on common posts plus user suggested alternatives.
Hence, a higher number means a more popular project.
Related posts
- Creating an open source chat bot like ChatGPT for my own dataset without GPU?
- Looks like some Taliban fighters are getting burnt out working the 9-5 grind
- H3 - a new generative language models that outperforms GPT-Neo-2.7B with only *2* attention layers! In H3, the researchers replace attention with a new layer based on state space models (SSMs). With the right modifications, they find that it can outperform transformers.
- Where is the line for AI and where does ChatGPT stand?
- Teaser trailer for "The Diary of Sisyphus" (2023), the world's first feature film written by an artificial intelligence (GPT-NEO) and produced Briefcase Films, my indie film studio based in Northern Italy