GPT4All Compatibility Ecosystem

This commit is contained in:
Andriy Mulyar 2023-04-05 12:48:54 -04:00 committed by GitHub
parent 1eeaa5c8ee
commit e16cbeb4b7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -81,6 +81,17 @@ We are working on a GPT4All that does not have this limitation right now.
You can pass any of the [huggingface generation config params](https://huggingface.co/docs/transformers/main_classes/text_generation#transformers.GenerationConfig) in the config.
# GPT4All Compatibility Ecosystem
Edge models in the GPT4All Ecosystem. Please PR as the [community grows](https://huggingface.co/models?sort=modified&search=4bit).
Feel free to convert this to a more structured table.
- [gpt4all](https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized.bin)
- [gpt4all-unfiltered](https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-unfiltered-quantized.bin)
- [ggml-vicuna-7b-4bit](https://huggingface.co/eachadea/ggml-vicuna-7b-4bit)
- [vicuna-13b-GPTQ-4bit-128g](https://huggingface.co/anon8231489123/vicuna-13b-GPTQ-4bit-128g)
- [LLaMa-Storytelling-4Bit](https://huggingface.co/GamerUntouch/LLaMa-Storytelling-4Bit)
# Roadmap
## Short Term
- <span style="color:green">(IN PROGRESS)</span> Train a GPT4All model based on GPTJ to alleviate llama distribution issues.