G-retriever (GNN+LLM) example w/ demo #9154
Closed
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
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
…ince they are unreasonable and exist since the linter thinks all atributes of a graph can either be a value or None
…ince they are unreasonable and exist since the linter thinks all atributes of a graph can either be a value or None
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #9154 +/- ##
==========================================
- Coverage 90.02% 89.58% -0.45%
==========================================
Files 470 470
Lines 30165 30165
==========================================
- Hits 27157 27023 -134
- Misses 3008 3142 +134 ☔ View full report in Codecov by Sentry. |
|
made a new PR: #9167 |
rusty1s
added a commit
that referenced
this pull request
Sep 13, 2024
1. #9462 2. #9480 3. #9481 4. **->** #9167 --- repro: Latest NVIDIA PyG container + `git config --global credential.helper store; huggingface-cli login; cd /opt/pyg; pip uninstall -y torch-geometric; rm -rf pytorch_geometric; git clone -b gnn-llm-model-integration https://github.com/pyg-team/pytorch_geometric.git; cd /opt/pyg/pytorch_geometric; pip install .; pip install peft datasets transformers pcst_fast sentencepiece; python3 examples/llm_plus_gnn/g_retriever.py` old PR: #9154 note: pure cpu is 220x slower than pure GPU using a single Grace Hopper (for llama-7b) info: tried gemma, performs worse in all train/val/test metrics. most likely needs some tuning, will leave this as future work as part of the community sprint to try many LLM and GNN combos and tune them. Therefore keeping the default llama2 the new gemma-v2 is also much worse than llama2 --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Akihiro Nitta <[email protected]> Co-authored-by: rusty1s <[email protected]>
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.
GNN reduces hallucinations by: ~62.0%
Note: hallucinations detected by regex hence the ~
old PR: #8984 (closed)