gpt4all-chat
llm-experiments
gpt4all-chat | llm-experiments | |
---|---|---|
3 | 2 | |
1,188 | 24 | |
- | - | |
9.3 | 6.4 | |
12 months ago | 11 months ago | |
C++ | Python | |
GNU General Public License v3.0 or later | GNU Affero General Public License v3.0 |
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.
gpt4all-chat
-
GPT4All releases one click install for Mac,win64,Linux with new GPT-J basemodel
LOL, the whole code is available here with the entire commit history and everyone who has committed. This is an open source project. https://github.com/nomic-ai/gpt4all-chat But go ahead with your scare mongering.
- ChatGPT4 is completely on rails.
llm-experiments
-
ChatGPT4 is completely on rails.
I think as a foundational model, LLaMA has a lot of untapped potential. For kicks, I ran text-davinci-003 (GPT-3.5 ) through lm-harness the other day and it slots in between llama-30b-q4 and llama-30b-q4. Note, GPT-3 is a 175b model, so that's really impressive. https://github.com/AUGMXNT/llm-experiments/blob/main/01-lm-eval.md
-
Benchmarks for LLMs on Consumer Hardware
I just spent $90 in OpenAPI credits to run the same `lm-harness` tests against `text-davinci-003` and it looks like it slots in between 13Bq8 and 30Bq4 on the test results: https://github.com/AUGMXNT/llm-experiments/blob/main/01-lm-eval.md
What are some alternatives?
ChatGPT_DAN - ChatGPT DAN, Jailbreaks prompt
MiniGPT-4 - Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
web-llm - Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.
gpt4all - gpt4all: run open-source LLMs anywhere
Learn_Prompting - Prompt Engineering, Generative AI, and LLM Guide by Learn Prompting | Join our discord for the largest Prompt Engineering learning community
llama-cpp-python - Python bindings for llama.cpp
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.