ColBERT
FinGPT
ColBERT | FinGPT | |
---|---|---|
4 | 11 | |
2,524 | 11,650 | |
7.0% | 3.9% | |
8.4 | 9.5 | |
about 1 month ago | 25 days ago | |
Python | Jupyter Notebook | |
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.
ColBERT
-
Why Vector Compression Matters
I’ll conclude by explaining how vector compression relates to ColBERT, a higher-level technique that Astra DB customers are starting to use successfully.
-
How ColBERT Helps Developers Overcome the Limits of Retrieval-Augmented Generation
ColBERT is a new way of scoring passage relevance using a BERT language model that substantially solves the problems with DPR. This diagram from the first ColBERT paper shows why it’s so exciting:
- FLaNK Stack 05 Feb 2024
-
New free tool that uses fine-tuned BERT model to surface answers from research papers
ColBERT and successors for retrieval.
FinGPT
-
GPT-4, without specialized training, beat a GPT-3.5 class model that cost $10B
There is also the open source FinGPT, that is claimed to beat GPT4 in some benchmarks at a fine tuning cost of $17.25.
https://github.com/AI4Finance-Foundation/FinGPT
- FLaNK Stack 05 Feb 2024
-
Ask HN: How to Get into Quantitative Trading?
https://github.com/AI4Finance-Foundation/FinGPT
[1] Zipline is a Pythonic algorithmic trading library
- FinGPT
- FLaNK Stack Weekly for 20 June 2023
- GPT but for the Finance Industry
-
FinGPT: Open-Source Financial Large Language Models
Code: https://github.com/AI4Finance-Foundation/FinGPT
- Is FinGPT Coming?
What are some alternatives?
qdrant - Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
modelscope - ModelScope: bring the notion of Model-as-a-Service to life.
similarity - TensorFlow Similarity is a python package focused on making similarity learning quick and easy.
EasyCV - An all-in-one toolkit for computer vision
elasticsearch-learning-to-rank - Plugin to integrate Learning to Rank (aka machine learning for better relevance) with Elasticsearch
keep - The open-source alert management and AIOps platform
Milvus - A cloud-native vector database, storage for next generation AI applications
prompt-engineering - Tips and tricks for working with Large Language Models like OpenAI's GPT-4.
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
StanfordQuadruped
awesome-semantic-search - A curated list of awesome resources related to Semantic Search🔎 and Semantic Similarity tasks.
alpaca_eval - An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.