maddes8cht's picture
"Update README.md"
0157d8e
|
raw
history blame
4.45 kB
metadata
license: apache-2.0

banner

I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information

persimmon-8b-chat - GGUF

Persimmon is a Large language Model from Adept AI. It is trained from Scratch with a context legth of 16k, which is 4 times the context size of LLaMA2 or ChatGPT and 8 times that of GPT-3


Brief

This is a preview of adepts persimmon chat model. It i snot based on the model published at https://huggingface.co/adept/persimmon-8b-chat but on the ones released on the tar files in https://github.com/persimmon-ai-labs/adept-inference. As these seems to be slightly different, models based on the huggingface release will follow as soon as possible.

Note: These models do not seem to work with cuda acceleration at the moment.

If you are using the Cublas version of Llama.cpp, you need to set --n-gpu-layers 0 for it to work. (At a later date this may work again with Cuda, so feel free to play with this setting)


About GGUF format

gguf is the current file format used by the ggml library. A growing list of Software is using it and can therefore use this model. The core project making use of the ggml library is the llama.cpp project by Georgi Gerganov

Quantization variants

There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:

Legacy quants

Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are legacy quantization types. Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.

Note:

Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not real K-quants. More details can be found in affected model descriptions. (This mainly refers to Falcon 7b and Starcoder models)

K-quants

K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load. So, if possible, use K-quants. With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.


Original Model Card:

At Adept, we’re working towards an AI agent that can help people do anything they need to do on a computer. We’re not in the business of shipping isolated language models (LMs)—this was an early output of the model scaling program that will support our products.

We trained it from scratch using a context size of 16K. Many LM use cases are context-bound; our model has 4 times the context size of LLaMA2 and 8 times that of GPT-3, MPT, etc.

This is a chat finetuned version of the base model. The best prompt to use is:

human: [some query]

adept:

See https://www.adept.ai/blog/persimmon-8b for more info

End of original Model File

Please consider to support my work

Coming Soon: I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.

GitHub Stack Exchange GitHub HuggingFace Twitter