Aligner/nemotron5 #11264
Draft
Aligner/nemotron5 #11264
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
Signed-off-by: JRD971000 <[email protected]>
Signed-off-by: JRD971000 <[email protected]>
Signed-off-by: JRD971000 <[email protected]>
Signed-off-by: JRD971000 <[email protected]>
Signed-off-by: adithyare <[email protected]>
Signed-off-by: arendu <[email protected]>
Signed-off-by: adithyare <[email protected]>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| if dist_ckpt_args.spec is not None: | ||
| mamba_stack_spec = import_module(dist_ckpt_args.spec) | ||
| else: | ||
| raise ("You must provide a valid Mamba layer spec!") |
Check failure
Code scanning / CodeQL
Illegal raise Error
| @@ -165,30 +421,47 @@ | |||
| nemo_config.model.tokenizer.library = tokenizer_library | |||
| nemo_config.model.tokenizer.type = tokenizer_type | |||
| nemo_config.model.tokenizer.model = tokenizer_model | |||
|
|
|||
| nemo_config.model.tokenizer.vocab_file = tokenizer_vocab | |||
Check failure
Code scanning / CodeQL
Potentially uninitialized local variable Error
|
|
||
| nemo_config.model.tokenizer.vocab_file = tokenizer_vocab | ||
| if args.source_dist_ckpt: | ||
| nemo_config.model.kv_channels = dist_ckpt_args.kv_channels |
Check failure
Code scanning / CodeQL
Potentially uninitialized local variable Error
| nemo_model_from_pyt.save_to(args.output_path) | ||
| nemo_model = nemo_model.to(dtype=dtype) | ||
| if args.check_fwd_pass: | ||
| assert mcore_model is not None |
Check failure
Code scanning / CodeQL
Potentially uninitialized local variable Error
…to aligner/nemotron5
Signed-off-by: adithyare <[email protected]>
Signed-off-by: arendu <[email protected]>
| ) | ||
| Utils.inited = True | ||
|
|
||
| except: |
Check notice
Code scanning / CodeQL
Empty except Note
| ) | ||
| Utils.inited = True | ||
|
|
||
| except: |
Check notice
Code scanning / CodeQL
Except block handles 'BaseException' Note
Signed-off-by: Gerald Shen <[email protected]>
Signed-off-by: adithyare <[email protected]>
Signed-off-by: Ali Taghibakhshi <[email protected]>
…to aligner/nemotron5
Signed-off-by: arendu <[email protected]>
Signed-off-by: arendu <[email protected]>
Signed-off-by: adithyare <[email protected]>
…to aligner/nemotron5
| @@ -13,6 +13,8 @@ | |||
| # limitations under the License. | |||
|
|
|||
| import torch | |||
| import torch.nn.functional as F | |||
| from omegaconf import open_dict | |||
Check notice
Code scanning / CodeQL
Unused import Note
Signed-off-by: arendu <[email protected]>
…to aligner/nemotron5
Signed-off-by: arendu <[email protected]>
Signed-off-by: Gerald Shen <[email protected]>
…or Aligner (#10863) * fix(export): update API for disabling device reassignment in TRTLLM for Aligner [feat] Upgrade nemo-export path for aligner to TRTLLM-v12 and use python runtime Signed-off-by: Terry Kong <[email protected]> fix: forgot to always set _disable_torch_cuda_device_set Signed-off-by: Terry Kong <[email protected]> Signed-off-by: Terry Kong <[email protected]> Apply isort and black reformatting Signed-off-by: terrykong <[email protected]> invert torch device set Signed-off-by: Terry Kong <[email protected]> * remove comment Signed-off-by: Terry Kong <[email protected]> --------- Signed-off-by: Terry Kong <[email protected]>
Signed-off-by: adithyare <[email protected]>
…to aligner/nemotron5
Signed-off-by: arendu <[email protected]>
Signed-off-by: haifengqian <[email protected]>
Signed-off-by: Jiaqi Zeng <[email protected]>
Signed-off-by: HeyyyyyyG <[email protected]>
… sequence in a batch
In theory, with the previous implementation it would have been possible for a thread to re-use the output from a previous batch, if it happened to grab the lock before the thread with queryid == 0.
This can give a small speedup for free, since usually batched queries all come in within <0.5s
Signed-off-by: Gerald Shen <[email protected]>
Signed-off-by: Gerald Shen <[email protected]>
This is because those tokens are typically added in the code (e.g. for padding purpose) and we do not want them to be part of the response.
Signed-off-by: Jiaqi Zeng <[email protected]>
Signed-off-by: Ali Taghibakhshi <[email protected]>
|
beep boop 🤖: 🙏 The following files have warnings. In case you are familiar with these, please try helping us to improve the code base. Your code was analyzed with PyLint. The following annotations have been identified: Thank you for improving NeMo's documentation! |
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.
What does this PR do ?
place to make all changes to support nemotron5 training
Collection: [Note which collection this PR will affect]
Changelog
Usage
# Add a code snippet demonstrating how to use thisGitHub Actions CI
The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.
The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information