feat(llama2): add template for chat messages (#782)

Co-authored-by: Aman Karmani <aman@tmm1.net>

Lays some of the groundwork for LLAMA2 compatibility as well as other future models with complex prompting schemes.

Started small refactoring in pkg/model/loader.go regarding template loading. Currently still a part of ModelLoader, but should be easy to add template loading for situations other than overall prompt templates and the new chat-specific per-message templates
Adds support for new chat-endpoint-specific, per-message templates as an alternative to the existing Role: XYZ sprintf method.
Includes a temporary prompt template as an example, since I have a few questions before we merge in the model-gallery side changes (see )
Minor debug logging changes.
This commit is contained in:
Dave 2023-07-22 11:31:39 -04:00 committed by GitHub
parent 5ee186b8e5
commit c6bf67f446
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 237 additions and 123 deletions

View file

@ -0,0 +1,7 @@
{{if eq .RoleName "assistant"}}{{.Content}}{{else}}
[INST]
{{if .SystemPrompt}}{{.SystemPrompt}}{{else if eq .RoleName "system"}}<<SYS>>{{.Content}}<</SYS>>
{{else if .Content}}{{.Content}}{{end}}
[/INST]
{{end}}