Available Models in Prompt based Skills

Models used in Generative Assistants

Here you may find a list of models that currently available for use in Generative Assistants.

model name	container name	model link	open-source?	size (billion parameters)	GPU usage	max tokens (prompt + response)	description
GPT-J 6B	transformers-lm-gptj	link	yes	6B	25GB	2,048 tokens	An open-source large language model. English-only, not fine-tuned for instruction following, not capable of code generation. For more details, refer to this GitHub repo
GPT-3.5	openai-api-davinci3	link	no (paid access via API)	supposedly, 175B	- (cannot be run locally)	4,097 tokens	Based on text-davinci-003 -- the largest and most capable of GPT-3/GPT-3.5 models family (featuring davinci, curie, babbage, ada models) not optimized for chat. Unlike earlier GPT-3 models, also able to understand and generate code. Unlike GPT-3.5 turbo, not optimised for chat. For more details, refer to OpenAI website.
ChatGPT	openai-api-chatgpt	link	no (paid access via API)	supposedly, 175B	- (cannot be run locally)	4,096 tokens	Based on gpt-3.5-turbo -- the most capable of the entire GPT-3/GPT-3.5 models family. Optimized for chat. Able to understand and generate code. For more details, refer to OpenAI website.
Open-Assistant SFT-1 12B	transformers-lm-oasst12b	link	yes	12B	26GB (half-precision)	5,120 tokens	An open-source large language model Open-Assistant SFT-1 12B Model. This is the first iteration English supervised-fine-tuning (SFT) model of the Open-Assistant project. It is based on a Pythia 12B that was fine-tuned on ~22k human demonstrations of assistant conversations collected through the https://open-assistant.io/ human feedback web app before March 7, 2023. The model is known to fail horribly at answering math and coding questions. This model is usable only for English conversations.