Draft: torch_geometric.nn.nlp.TXT2KG and examples/hotpot_qa.py for recall/precision eval
#9728
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
puririshi98
changed the title
torch_geometric.nn.nlp.TXT2KGtorch_geometric.nn.nlp.TXT2KG and examples/hotpot_qa.py for recall/precision eval
for more information, see https://pre-commit.ci
|
How difficult would it be to upgrade from Llama 2.0 to 3.1? |
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
im not sure what you mean. I dont use either for this PR. if your talking about the default model for the g_retriever.py example, it should be trivial for you to swap in any LLM or GNN, thats the whole point of the framework. |
|
needs rebase onto master |
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
…tron-70b, but its still the default
for more information, see https://pre-commit.ci
…tron-70b, but its still the default
for more information, see https://pre-commit.ci
|
Support for Llama 3.3 79B out today that performs as well as Llama 3.1 405B for much less money… would be awesome! |
Co-authored-by: riship <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
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Outdated suggestions cannot be applied.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.
Many RAG Q+A datasets do not have existing KGs to work with. KG creation is an essential step in the real world. This is a simplistic approach, in the future hope to have more refined approaches to replace this
Deliverable: example of making a standard RAG benchmark like hotpotQA into a KG and how to measure precision/recall of retrieval
Basing on a copy of #9666, will change base of PR to master once his work is merged
Now works at small scale, testing at full scale (10% of hotpot QA) soon. Goal is >=.5 precision/recall