G Retriever Experiments and Improvements (full) #9666
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
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
Co-authored-by: Akihiro Nitta <[email protected]>
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
|
Aiming to resolve the merge conflicts by EoW. I can also break this PR down further if needed. |
# Conflicts: # CHANGELOG.md # test/nn/models/test_g_retriever.py # torch_geometric/datasets/__init__.py # torch_geometric/datasets/web_qsp_dataset.py # torch_geometric/nn/models/g_retriever.py # torch_geometric/nn/nlp/llm.py # torch_geometric/nn/nlp/sentence_transformer.py
for more information, see https://pre-commit.ci
|
Merge Conflicts are resolved. Currently running the following tests to make sure nothing has broken:
|
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
…iments # Conflicts: # examples/llm_plus_gnn/README.md # examples/llm_plus_gnn/g_retriever.py
for more information, see https://pre-commit.ci
zaristei
commented
Oct 4, 2024
| hallucinates_df.to_csv(root_dir + "/hallucinates_df.csv", index=False) | ||
|
|
||
|
|
||
| def minimal_demo(gnn_llm_eval_outs, dataset, lr, epochs, batch_size, |
There was a problem hiding this comment.
@puririshi98 FYI: I re-added the minimal demo to this PR, but didn't include it in the critical path of running this file, not sure whether you were going to re-add this minimal demo in a separate PR.
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Outdated suggestions cannot be applied.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.
Follow up to PR 9597. Includes multiple changes related to LLM+GNN experiments and scaling up to a remote backend. Including: