-
Notifications
You must be signed in to change notification settings - Fork 370
Conversation
ea512a7
to
58d5a93
Compare
@@ -28,51 +35,53 @@ to support GPU inference in the future through alternate backends. | |||
|
|||
Currently, the following models are supported: | |||
|
|||
- [BLOOM](https://huggingface.co/docs/transformers/model_doc/bloom) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we list some interesting examples of these? BLOOM has BLOOMZ, GPT-J has GPT4All, etc
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I don't understand this request.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
So the README has
Currently, the following models are supported:
where GPT-NeoX and LLaMA have some examples of models that use those architectures. It would be nice to have some examples for BLOOM, GPT-2, GPT-J and MPT too (even if it's just "MPT" for the last one), just so that it doesn't look weirdly imbalanced.
Those models could also have links to the descriptions (e.g. linking Alpaca to the Stanford article), but I leave that up to you.
3b37127
to
3a7fcfa
Compare
3a7fcfa
to
7ecea8e
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pretty much good to go, just those last two things. Once they're sorted I'll merge
359135f
to
0d88ac8
Compare
0d88ac8
to
bdd89ce
Compare
Rendered version can be seen here https://github.com/danforbes/llama-rs/blob/dfo/docs/readme/README.md