local-guidance
A guidance language for controlling large language models. (by paolorechia)
localLLM_langchain
Local LLM Agent with Langchain (by QuangBK)
| local-guidance | localLLM_langchain | |
|---|---|---|
| 2 | 2 | |
| 9 | 46 | |
| - | - | |
| 8.7 | 3.6 | |
| 12 months ago | 12 months ago | |
| Jupyter Notebook | Jupyter Notebook | |
| MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
local-guidance
Posts with mentions or reviews of local-guidance.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-05-18.
localLLM_langchain
Posts with mentions or reviews of localLLM_langchain.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-05-18.
-
local LLM agent?
I was able to make a dumb bot (react framework) using wizardlm 13b and 30b (1.1 for 13b) (using something similar to this: https://github.com/QuangBK/localLLM_langchain/blob/main/localLLM_agent.ipynb, without langchain. But it seems like it really struggles with following the correct format when giving the output. Sometimes, its thought is to search, but instead, it parses a web page. I have tried using natural language and json format output. I've tweeked the prompt several times to varying degrees of success. I've played with the temperature with some success.
-
I made a simple agent demo with Guidance and wizard-mega-13B-GPTQ, feel quite promising.
Also, you can compare Langchain and Guidance here: Guidance Agent and Langchain Agent
What are some alternatives?
When comparing local-guidance and localLLM_langchain you can also consider the following projects:
llama-cpp-python - Python bindings for llama.cpp
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
localLLM_guidance - Local LLM ReAct Agent with Guidance
guidance - A guidance language for controlling large language models.