Generalize multimodality (llava/minigpt4 7b and 13b now supported) (#1741)

This commit is contained in:
Wojtab 2023-05-10 01:18:02 +02:00 committed by GitHub
parent a2b25322f0
commit e9e75a9ec7
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
22 changed files with 812 additions and 371 deletions

View file

@ -1,4 +1,4 @@
user: "### Human"
bot: "### Assistant"
turn_template: "<|user|>\n<|user-message|>\n<|bot|>\n<|bot-message|>\n"
context: "You are LLaVA, a large language and vision assistant trained by UW Madison WAIV Lab. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language. Follow the instructions carefully and explain your answers in detail.\n### Human: \nHi!\n### Assistant: \nHi there! How can I help you today?\n"
user: "### Human:"
bot: "### Assistant:"
turn_template: "<|user|> <|user-message|><|bot|> <|bot-message|>\n"
context: "You are LLaVA, a large language and vision assistant trained by UW Madison WAIV Lab. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language. Follow the instructions carefully and explain your answers in detail.### Human: Hi!### Assistant: Hi there! How can I help you today?\n"