self-instruct
CodeCapypara
| self-instruct | CodeCapypara | |
|---|---|---|
| 3 | 1 | |
| 3,666 | 94 | |
| - | - | |
| 2.3 | 10.0 | |
| about 1 year ago | about 1 year ago | |
| Python | Python | |
| Apache License 2.0 | 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.
self-instruct
-
The next generation of AI for developers and Google Workspace
When they say Augment your dataset with synthetic data on https://developers.googleblog.com/2023/03/announcing-palm-ap... do they mean something like this https://github.com/yizhongw/self-instruct ?
-
Alpaca- An Instruct Tuned Llama 7B. Responses on par with txt-DaVinci-3. Demo up
It says
> We train the Alpaca model on 52K instruction-following demonstrations generated in the style of self-instruct using text-davinci-003
Which leads to self-instruct https://github.com/yizhongw/self-instruct
From a glimpse they used a LM to classify instructions & train the model which IMHO very similar to RLHF
- Alpaca: A Strong Open-Source Instruction-Following Model
CodeCapypara
-
[R] CodeCapybara: Another open source model for code generation based on instruction tuning, outperformed Llama and CodeAlpaca
The model can be accessed here: https://github.com/AI4Code-Research/CodeCapypara
What are some alternatives?
ChatGLM-6B - ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
LLaMA-LoRA-Tuner - UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.
stanford_alpaca - Code and documentation to train Stanford's Alpaca models, and generate the data.
CodeCapybara - Open-source Self-Instruction Tuning Code LLM
LongForm - Reverse Instructions to generate instruction tuning data with corpus examples
example-scalping - A working example algorithm for scalping strategy trading multiple stocks concurrently using python asyncio
llama.cpp - LLM inference in C/C++
example-hftish - Example Order Book Imbalance Algorithm
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
ExpertLLaMA - An opensource ChatBot built with ExpertPrompting which achieves 96% of ChatGPT's capability.
replika-research - Replika.ai Research Papers, Posters, Slides & Datasets
safe-rlhf - Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback