Bringup tt-torch models in forge #1314
Open
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
|
||||||||||||||
|
||||||||||||||||||
|
||||||||||||||
1 similar comment
|
||||||||||||||
kamalrajkannan78
force-pushed
the
kkannan/tt_torch_models_bringup
branch
from
66ff210 to
09430d9
Compare
|
||||||||||||||
|
||||||||||||||
|
||||||||||||||
|
||||||||||||||
nvukobratTT
reviewed
Feb 25, 2025
kamalrajkannan78
force-pushed
the
kkannan/tt_torch_models_bringup
branch
2 times, most recently
from
899912e to
823a81e
Compare
|
||||||||||||||||||||||||
3 similar comments
|
||||||||||||||||||||||||
|
||||||||||||||||||||||||
|
||||||||||||||||||||||||
kamalrajkannan78
force-pushed
the
kkannan/tt_torch_models_bringup
branch
from
823a81e to
da83043
Compare
|
||||||||||||||||||||||
3 similar comments
|
||||||||||||||||||||||
|
||||||||||||||||||||||
|
||||||||||||||||||||||
kamalrajkannan78
force-pushed
the
kkannan/tt_torch_models_bringup
branch
6 times, most recently
from
e8ebdde to
8b18209
Compare
kamalrajkannan78
requested review from
vkovinicTT and
mstojkovicTT
as code owners
kamalrajkannan78
requested review from
pilkicTT and
dgolubovicTT
as code owners
kamalrajkannan78
force-pushed
the
kkannan/tt_torch_models_bringup
branch
from
8b18209 to
8a3aab6
Compare
|
||||||||||||||
|
||||||||||||||
|
||||||||||||||
|
||||||||||||||
vkovinicTT
requested changes
Feb 27, 2025
|
|
||
|
|
||
| def load_model(): | ||
| model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-1b1") |
There was a problem hiding this comment.
Maybe pass the model_variant as param?
|
|
||
| def load_input(): | ||
| test_input = "This is a sample text from " | ||
| tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-1b1", padding_side="left") |
|
|
||
|
|
||
| def load_model(): | ||
| model = GLPNForDepthEstimation.from_pretrained("vinvino02/glpn-kitti") |
There was a problem hiding this comment.
Pass model_variant as param.
| def load_input(): | ||
| url = "http://images.cocodataset.org/val2017/000000039769.jpg" | ||
| image = Image.open(requests.get(url, stream=True).raw) | ||
| processor = GLPNImageProcessor.from_pretrained("vinvino02/glpn-kitti") |
There was a problem hiding this comment.
Pass model_variant as param.
|
|
||
|
|
||
| def load_model(): | ||
| model = MgpstrForSceneTextRecognition.from_pretrained("alibaba-damo/mgp-str-base") |
There was a problem hiding this comment.
Pass model_variant as param.
| def load_input(): | ||
| url = "https://i.postimg.cc/ZKwLg2Gw/367-14.png" | ||
| image = Image.open(requests.get(url, stream=True).raw).convert("RGB") | ||
| processor = MgpstrProcessor.from_pretrained("alibaba-damo/mgp-str-base") |
There was a problem hiding this comment.
Pass model_variant as param.
|
|
||
|
|
||
| def load_input(): | ||
| url = "https://i.postimg.cc/ZKwLg2Gw/367-14.png" |
There was a problem hiding this comment.
Should we really take those images? What do others think?
|
|
||
|
|
||
| def load_model(): | ||
| model = AutoModelForImageSegmentation.from_pretrained("briaai/RMBG-2.0", trust_remote_code=True) |
There was a problem hiding this comment.
Pass model_variant as param.
|
|
||
|
|
||
| def load_model(): | ||
| model = AutoModelForObjectDetection.from_pretrained("hustvl/yolos-tiny") |
There was a problem hiding this comment.
Pass model_variant as param.
ashokkumarkannan1
requested changes
Feb 27, 2025
There was a problem hiding this comment.
Great Work @kamalrajkannan78 . Thanks for the PR. Left few review comments. Please address those comments.... :)
| module_name = build_module_name( | ||
| framework=Framework.PYTORCH, | ||
| model="albert", | ||
| task=Task.QA, |
There was a problem hiding this comment.
variant missing?
| module_name = build_module_name( | ||
| framework=Framework.PYTORCH, | ||
| model="albert", | ||
| task=Task.SEQUENCE_CLASSIFICATION, |
There was a problem hiding this comment.
missing variant?
Comment on lines
+97
to
+98
| variants = ["bert-large-cased-whole-word-masking-finetuned-squad", "phiyodr/bert-large-finetuned-squad2"] | ||
|
|
| module_name = build_module_name( | ||
| framework=Framework.PYTORCH, | ||
| model="bloom", | ||
| source=Source.HUGGINGFACE, |
There was a problem hiding this comment.
missing variant? pls check all the model test files and add the variants
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.
Summary
This PR addresses Issue #1321 by porting models from tt-torch to tt-forge. The current compilation status of these models are available in the logs.
A list of skipped models along with the reasons for their exclusion can be found in Issue #1339. Any models that were missed in this PR will be included in PR #1337.
Note:
Logs: