FinGPT
alpaca_eval
FinGPT | alpaca_eval | |
---|---|---|
11 | 4 | |
11,586 | 1,160 | |
3.4% | 12.0% | |
9.5 | 9.6 | |
21 days ago | about 13 hours ago | |
Jupyter Notebook | Jupyter Notebook | |
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.
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?
alpaca_eval
-
UltraLM-13B reaches top of AlpacaEval leaderboard
Alpaca Eval is open source and was developed by the same team who trained the alpaca model afaik. It is not like what you said in the other comment
-
[P] AlpacaEval : An Automatic Evaluator for Instruction-following Language Models
I have been going deep in this space for my can-ai-code project and was looking at the config that WizardLM was run with: https://github.com/tatsu-lab/alpaca_eval/blob/main/src/alpaca_eval/models_configs/wizardlm-13b/configs.yaml
an automatic evaluator that is easy to use, fast, cheap and validated against 20K human annotations. It actually has a higher agreement with majority vote of humans than a single human annotator! Of course, our method still has limitations which we discuss here!
What are some alternatives?
modelscope - ModelScope: bring the notion of Model-as-a-Service to life.
Local-LLM-Comparison-Colab-UI - Compare the performance of different LLM that can be deployed locally on consumer hardware. Run yourself with Colab WebUI.
EasyCV - An all-in-one toolkit for computer vision
DeepLearningExamples - State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
keep - The open-source alert management and AIOps platform
llm-search - Querying local documents, powered by LLM
prompt-engineering - Tips and tricks for working with Large Language Models like OpenAI's GPT-4.
alpaca_farm - A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.
StanfordQuadruped
medmcqa - A large-scale (194k), Multiple-Choice Question Answering (MCQA) dataset designed to address realworld medical entrance exam questions.
canal - 阿里巴巴 MySQL binlog 增量订阅&消费组件
language-planner - Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"