An implementation of model & data parallel GPT3-like models using the mesh-tensorflow library.
Source: EleutherAI/GPT-Neo
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Language Modelling | 9 | 18.75% |
Text Generation | 7 | 14.58% |
Code Generation | 5 | 10.42% |
Prompt Engineering | 3 | 6.25% |
Large Language Model | 2 | 4.17% |
Question Answering | 2 | 4.17% |
Fairness | 1 | 2.08% |
Chatbot | 1 | 2.08% |
Memorization | 1 | 2.08% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |