Embed Llama.cpp into Marsha for local usage #164
Draft
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…don't do that. Also some tweaks to the prompt and arg handling
|
70B took a lot longer (since only about 1/4th of the layers could fit on my GPU) required different params to llama.cpp that weren't predictable in any way, and actually did a worse job than 13B in my test run, unexpectedly. Going back to 13B for the faster iteration speed (it's on par with OpenAI response times, if not the quality). |
…en I set it as suggested it generated the desired output for the first time!
…pts and also lower the temperature because Llama v2 is a bit 'wilder' than ChatGPT
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Currently getting to the third stage with Llama 2 13B but failing there.