From b525d22605e722800ee8049855d77f69e3fa2afe Mon Sep 17 00:00:00 2001 From: Yih-Dar <2521628+ydshieh@users.noreply.github.com> Date: Fri, 24 Jan 2025 20:07:07 +0100 Subject: [PATCH 1/2] Add `Rocketknight1` to `self-comment-ci.yml` (#35881) my bad Co-authored-by: ydshieh Signed-off-by: kurtis --- .github/workflows/self-comment-ci.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/self-comment-ci.yml b/.github/workflows/self-comment-ci.yml index f33a6f91f953..3f2b637e047c 100644 --- a/.github/workflows/self-comment-ci.yml +++ b/.github/workflows/self-comment-ci.yml @@ -30,7 +30,7 @@ jobs: runs-on: ubuntu-22.04 name: Get PR number # For security: only allow team members to run - if: ${{ github.event.issue.state == 'open' && contains(fromJSON('["ydshieh", "ArthurZucker", "zucchini-nlp", "qubvel", "molbap", "gante", "LysandreJik", "Cyrilvallez"]'), github.actor) && (startsWith(github.event.comment.body, 'run-slow') || startsWith(github.event.comment.body, 'run slow') || startsWith(github.event.comment.body, 'run_slow')) }} + if: ${{ github.event.issue.state == 'open' && contains(fromJSON('["ydshieh", "ArthurZucker", "zucchini-nlp", "qubvel", "molbap", "gante", "LysandreJik", "Cyrilvallez", "Rocketknight1"]'), github.actor) && (startsWith(github.event.comment.body, 'run-slow') || startsWith(github.event.comment.body, 'run slow') || startsWith(github.event.comment.body, 'run_slow')) }} outputs: PR_NUMBER: ${{ steps.set_pr_number.outputs.PR_NUMBER }} steps: From c03918423aebfac65312870bc2365a6b14e3289d Mon Sep 17 00:00:00 2001 From: kurtis Date: Mon, 2 Mar 2026 15:27:02 -0600 Subject: [PATCH 2/2] fix ibm-fs Repo-Jacking Signed-off-by: kurtis --- docs/source/en/model_doc/bamba.md | 4 ++-- src/transformers/models/bamba/configuration_bamba.py | 2 +- tests/models/bamba/test_modeling_bamba.py | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/source/en/model_doc/bamba.md b/docs/source/en/model_doc/bamba.md index 4ea8475edb88..2ec9ef8c3365 100644 --- a/docs/source/en/model_doc/bamba.md +++ b/docs/source/en/model_doc/bamba.md @@ -49,8 +49,8 @@ Tips: ```python from transformers import AutoModelForCausalLM, AutoTokenizer -model = AutoModelForCausalLM.from_pretrained("ibm-fms/Bamba-9B") -tokenizer = AutoTokenizer.from_pretrained("ibm-fms/Bamba-9B") +model = AutoModelForCausalLM.from_pretrained("ibm-ai-platform/Bamba-9B") +tokenizer = AutoTokenizer.from_pretrained("ibm-ai-platform/Bamba-9B") message = ["Mamba is a snake with following properties "] inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False) diff --git a/src/transformers/models/bamba/configuration_bamba.py b/src/transformers/models/bamba/configuration_bamba.py index f84d63ec04a9..14d2967bc919 100644 --- a/src/transformers/models/bamba/configuration_bamba.py +++ b/src/transformers/models/bamba/configuration_bamba.py @@ -25,7 +25,7 @@ class BambaConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`BambaModel`]. It is used to instantiate a BambaModel model according to the specified arguments, defining the model architecture. Instantiating a configuration - with defaults taken from [ibm-fms/Bamba-9.8b-2.2T-hf](https://huggingface.co/ibm-fms/Bamba-9.8b-2.2T-hf). + with defaults taken from [ibm-ai-platform/Bamba-9.8b-2.2T-hf](https://huggingface.co/ibm-ai-platform/Bamba-9.8b-2.2T-hf). The BambaModel is a hybrid [mamba2](https://github.com/state-spaces/mamba) architecture with SwiGLU. The checkpoints are jointly trained by IBM, Princeton, and UIUC. diff --git a/tests/models/bamba/test_modeling_bamba.py b/tests/models/bamba/test_modeling_bamba.py index 68da2fdf028a..c8b46bea959b 100644 --- a/tests/models/bamba/test_modeling_bamba.py +++ b/tests/models/bamba/test_modeling_bamba.py @@ -496,7 +496,7 @@ class BambaModelIntegrationTest(unittest.TestCase): @classmethod def setUpClass(cls): - model_id = "ibm-fms/Bamba-9B" + model_id = "ibm-ai-platform/Bamba-9B" cls.model = BambaForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True) cls.tokenizer = AutoTokenizer.from_pretrained(model_id)