⏪ revert back to 3-layer micro model #497
Conversation
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
|
bot:test |
|
|
||
| - name: "Download HF models" | ||
| if: ( steps.changed-src-files.outputs.any_changed == 'true' && steps.cache_restore.outputs.cache-hit != 'true' ) | ||
| if: ( steps.changed-src-files.outputs.any_changed == 'true' && steps.cache_restore.outputs.cache-hit == 'true' ) |
There was a problem hiding this comment.
temporary change to get GH to download the older revision
|
FYI bot test seems to be fine with the 3 layer model! |
|
|
||
| - name: "Download HF models" | ||
| if: ( steps.changed-src-files.outputs.any_changed == 'true' && steps.cache_restore.outputs.cache-hit != 'true' ) | ||
| if: ( steps.changed-src-files.outputs.any_changed == 'true' && steps.cache_restore.outputs.cache-hit == 'true' ) |
There was a problem hiding this comment.
This means you will have both revisions:
- 4 layer model from the cache
- 3 layer model downloaded with revision
Making all the tests work. If you bypass the cache, I reckon some tests will break like in PR #499
There was a problem hiding this comment.
Once the 3 layer model is verified, I don't think we need the 4 layer anymore, so we should only be using one revision of the model at all places
There was a problem hiding this comment.
Ideally the fix has to be that we delete the old cache and populate it with the 3 layer revision and merge this PR right?
There was a problem hiding this comment.
I think it needs more code/test changes to make sure we don't use the latest/main revision of the tiny granite model anymore/anywhere.
Kicking of a test run here that is not also still using the old cached model: #502
There was a problem hiding this comment.
Yup:
E huggingface_hub.errors.LocalEntryNotFoundError: Cannot find an appropriate cached snapshot folder for the specified revision on the local disk and outgoing traffic has been disabled. To enable repo look-ups and downloads online, pass 'local_files_only=False' as input.
head_call_error = OfflineModeIsEnabled("Cannot access file since 'local_files_only=True' as been set. (repo_id: ibm-ai-platform/micro-g3.3-8b-instruct-1b, repo_type: model, revision: main, filename: config.json)") force_download = False, local_files_only = True
Also, need to not use the same revision key to download the FP8 model 🙄
ValueError: Unrecognized model in ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8
2 participants
Description
Revert back to 3-layer micro model.
Needs a fix from @ckadner (#499) where the HF models cache also contains the revision so that we can cache the right model.