Replace Falcon 🦅 model with Llama V2 🦙 for offline chat #352
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
- Download from huggingface - Plug in to GPT4All - Update prompts to fit the llama format - Note that this still is not performing extract_questions
…ed on llama format
…e-falcon-with-llamav2
debanjum
approved these changes
Jul 28, 2023
- Change llama-specific naming in chat_model methods to be general offline - Fix reasoning of assertion failure in one of the gpt4all actor tests
This was referenced Jul 28, 2023
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Outdated suggestions cannot be applied.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.
Incoming
GPT4Allsetup.extract_questionsflow. While Falcon's output wasn't high enough quality to actually use this functionality, Llama generally provides good enough responses (at least able to pass ~50% of the benchmark tests). That being said, query times might be too long to justify using this.Falcon->LlamaCloses #347