awesome-pretrained-chinese-nlp-models
ai_and_memory_wall
| awesome-pretrained-chinese-nlp-models | ai_and_memory_wall | |
|---|---|---|
| 1 | 1 | |
| 4,250 | 188 | |
| - | - | |
| 8.9 | 3.9 | |
| 4 days ago | about 2 months ago | |
| Python | ||
| MIT License | MIT License |
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.
awesome-pretrained-chinese-nlp-models
ai_and_memory_wall
-
Ask HN: Can you crowdfund the compute for GPT?
Depends on which version you're running. According to https://github.com/amirgholami/ai_and_memory_wall
What are some alternatives?
rust-bert - Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
GLM-130B - GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
educational-transformer - Easy-to-follow, educational implementation of the transformer model in PyTorch.
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
PaddleNLP - 👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.
hivemind - Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
ERNIE-text-classification-pytorch - This repo contains a PyTorch implementation of a pretrained ERNIE model for text classification.
RWKV-LM - RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
TencentPretrain - Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo
metaseq - Repo for external large-scale work