ABSA-PyTorch
transformers
Our great sponsors
ABSA-PyTorch | transformers | |
---|---|---|
1 | 175 | |
1,945 | 125,021 | |
- | 3.1% | |
0.0 | 10.0 | |
11 months ago | 5 days ago | |
Python | Python | |
MIT License | Apache License 2.0 |
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.
ABSA-PyTorch
-
Is there an open-source way to replicate entity-level sentiment from Google's Cloud Natural Language API?
I'm learning about NLP and was really impressed with Google's Natural Language API (demo). It seems that entity-level sentiment analysis is the future of NLP. Has anyone in the community come across open-source libraries that replicate the API (although of course with lower F1 scores). I found an excellent repo called ABSA-PyTorch but it seems that all the implementations are classification-based; that is, they return "positive/negative" rather than a spectrum between positive and negative. Is there a sub field of Aspect-Based Sentiment Analysis (ABSA) that isn't classification based? I wasn't able to find any keywords despite hours of Google searching.
transformers
-
Maxtext: A simple, performant and scalable Jax LLM
Is t5x an encoder/decoder architecture?
Some more general options.
The Flax ecosystem
https://github.com/google/flax?tab=readme-ov-file
or dm-haiku
https://github.com/google-deepmind/dm-haiku
were some of the best developed communities in the Jax AI field
Perhaps the “trax” repo? https://github.com/google/trax
Some HF examples https://github.com/huggingface/transformers/tree/main/exampl...
Sadly it seems much of the work is proprietary these days, but one example could be Grok-1, if you customize the details. https://github.com/xai-org/grok-1/blob/main/run.py
-
Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding
The HuggingFace transformers library already has support for a similar method called prompt lookup decoding that uses the existing context to generate an ngram model: https://github.com/huggingface/transformers/issues/27722
I don't think it would be that hard to switch it out for a pretrained ngram model.
-
AI enthusiasm #6 - Finetune any LLM you want💡
Most of this tutorial is based on Hugging Face course about Transformers and on Niels Rogge's Transformers tutorials: make sure to check their work and give them a star on GitHub, if you please ❤️
-
Schedule-Free Learning – A New Way to Train
* Superconvergence + LR range finder + Fast AI's Ranger21 optimizer was the goto optimizer for CNNs, and worked fabulously well, but on transformers, the learning rate range finder sadi 1e-3 was the best, whilst 1e-5 was better. However, the 1 cycle learning rate stuck. https://github.com/huggingface/transformers/issues/16013
-
Gemma doesn't suck anymore – 8 bug fixes
Thanks! :) I'm pushing them into transformers, pytorch-gemma and collabing with the Gemma team to resolve all the issues :)
The RoPE fix should already be in transformers 4.38.2: https://github.com/huggingface/transformers/pull/29285
My main PR for transformers which fixes most of the issues (some still left): https://github.com/huggingface/transformers/pull/29402
- HuggingFace Transformers: Qwen2
- HuggingFace Transformers Release v4.36: Mixtral, Llava/BakLlava, SeamlessM4T v2
- HuggingFace: Support for the Mixtral Moe
-
Paris-Based Startup and OpenAI Competitor Mistral AI Valued at $2B
If you want to tinker with the architecture Hugging Face has a FOSS implementation in transformers: https://github.com/huggingface/transformers/blob/main/src/tr...
If you want to reproduce the training pipeline, you couldn't do that even if you wanted to because you don't have access to thousands of A100s.
-
Fail to reproduce the same evaluation metrics score during inference.
I am aware that using mixed precision reduces the stability of weight and there will be little consistency but don't expect it to be this much. I have attached the graph of evaluation metrics. If someone can give me some insight into this issue, that would be great.
What are some alternatives?
clip-as-service - 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
nlphose - Enables creation of complex NLP pipelines in seconds, for processing static files or streaming text, using a set of simple command line tools. Perform multiple operation on text like NER, Sentiment Analysis, Chunking, Language Identification, Q&A, 0-shot Classification and more by executing a single command in the terminal. Can be used as a low code or no code Natural Language Processing solution. Also works with Kubernetes and PySpark !
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
entity-sentiment-analysis - Various ops for handling several entities in a document, perform anaphora resolution, clustering, etc.
llama - Inference code for Llama models
ERNIE - Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
obsei - Obsei is a low code AI powered automation tool. It can be used in various business flows like social listening, AI based alerting, brand image analysis, comparative study and more .
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
pytorch-sentiment-analysis - Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
huggingface_hub - The official Python client for the Huggingface Hub.