diff --git "a/data/prs.json" "b/data/prs.json"
--- "a/data/prs.json"
+++ "b/data/prs.json"
@@ -1,20 +1,284 @@
 [
   {
-    "additions": 8,
-    "author": "harshaljanjani",
+    "additions": 18,
+    "author": "JaredforReal",
     "author_association": "CONTRIBUTOR",
-    "body_excerpt": "### What does this PR do? The following failing tests were identified and fixed in this PR (grouped them together since they share related root causes OR the code changes were extremely minimal and didn't warrant separate PRs): \u2192 **Pi0**:\u2026",
+    "body_excerpt": "# What does this PR do? ### Get the rope operation right Before: NeoX split-half style After: GPT-J/interleaved style(`interleaved=True` same as `is_neox_style=Flase`) the right one ### Get rid of `F.relu` Reason: - `F.relu` works with `ac\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-44695-2",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 3,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45017",
+    "created_at": "2026-03-26T09:21:10Z",
+    "deletions": 28,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45017/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45017",
+    "labels": [],
+    "merged": false,
+    "number": 45017,
+    "review_comments_count": 5,
+    "state": "open",
+    "title": "[WIP][Fix] GLM 5 set `apply_rotary_pos_emb` to `is_neox_style=False` && remove `F.relu()`",
+    "updated_at": "2026-03-26T10:14:50Z"
+  },
+  {
+    "additions": 64,
+    "author": "inisis",
+    "author_association": "CONTRIBUTOR",
+    "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
+    "changed_files": 2,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 1,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45016",
+    "created_at": "2026-03-26T09:09:41Z",
+    "deletions": 4,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45016/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45016",
+    "labels": [],
+    "merged": false,
+    "number": 45016,
+    "review_comments_count": 0,
+    "state": "open",
+    "title": "fix: glm5 inference bug",
+    "updated_at": "2026-03-26T09:48:35Z"
+  },
+  {
+    "additions": 55,
+    "author": "pnehete23",
+    "author_association": "FIRST_TIME_CONTRIBUTOR",
+    "body_excerpt": "## What does this PR do? Fixes a `KeyError` in `_can_set_attn_implementation` and `_can_set_experts_implementation` when a model's module is absent from `sys.modules`. Fixes #45003 ## Root Cause Both `_can_set_attn_implementation` (line 19\u2026",
+    "changed_files": 2,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 0,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45015",
+    "created_at": "2026-03-26T08:52:10Z",
+    "deletions": 6,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45015/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45015",
+    "labels": [],
+    "merged": false,
+    "number": 45015,
+    "review_comments_count": 0,
+    "state": "open",
+    "title": "fix: guard sys.modules access in _can_set_attn/experts_implementation",
+    "updated_at": "2026-03-26T09:10:14Z"
+  },
+  {
+    "additions": 16,
+    "author": "ydshieh",
+    "author_association": "MEMBER",
+    "body_excerpt": "# What does this PR do? #30674 refactors the way we obtain CircleCI test files to run for each job. It always puts [\"tests\"] for `tests_hub`, so each commit of each PR will run it, no matter if there is any change to codebase. Let's reduce\u2026",
+    "changed_files": 1,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 1,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45014",
+    "created_at": "2026-03-26T08:52:04Z",
+    "deletions": 3,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45014/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45014",
+    "labels": [],
+    "merged": true,
+    "number": 45014,
+    "review_comments_count": 1,
+    "state": "closed",
+    "title": "Don't run `tests_hub` if no tests found",
+    "updated_at": "2026-03-26T09:32:39Z"
+  },
+  {
+    "additions": 256,
+    "author": "tarekziade",
+    "author_association": "MEMBER",
+    "body_excerpt": "# What does this PR do? Added a new checker that will `import transformers` and count the number of imported module. The checker will error out when it goes over a threshold - for instance if our code imports a lib like `torch` not lazily\u2026",
+    "changed_files": 3,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 2,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45013",
+    "created_at": "2026-03-26T07:47:23Z",
+    "deletions": 0,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45013/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45013",
+    "labels": [],
+    "merged": false,
+    "number": 45013,
+    "review_comments_count": 0,
+    "state": "open",
+    "title": "feature: added import complexity checker",
+    "updated_at": "2026-03-26T07:57:13Z"
+  },
+  {
+    "additions": 155,
+    "author": "tarekziade",
+    "author_association": "MEMBER",
+    "body_excerpt": "# What does this PR do? Cache to speed up ast walks, and ast tweak",
+    "changed_files": 2,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 1,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45012",
+    "created_at": "2026-03-26T07:10:45Z",
+    "deletions": 2,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45012/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45012",
+    "labels": [],
+    "merged": false,
+    "number": 45012,
+    "review_comments_count": 0,
+    "state": "open",
+    "title": "refactor: added cache in check_repo",
+    "updated_at": "2026-03-26T07:21:25Z"
+  },
+  {
+    "additions": 8,
+    "author": "kaixuanliu",
+    "author_association": "CONTRIBUTOR",
+    "body_excerpt": "@ydshieh Hi, can you help review? Thx!",
+    "changed_files": 1,
+    "cluster_id": "cluster-43324-12",
     "cluster_ids": [
-      "cluster-44695-2"
+      "cluster-43324-12"
     ],
     "cluster_role": "member",
+    "comments_count": 1,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45011",
+    "created_at": "2026-03-26T06:27:09Z",
+    "deletions": 0,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45011/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45011",
+    "labels": [],
+    "merged": false,
+    "number": 45011,
+    "review_comments_count": 0,
+    "state": "open",
+    "title": "skip 2 invalid test cases for pi0 model",
+    "updated_at": "2026-03-26T06:28:28Z"
+  },
+  {
+    "additions": 75,
+    "author": "dagecko",
+    "author_association": "FIRST_TIME_CONTRIBUTOR",
+    "body_excerpt": "## Fix: CI/CD Security Vulnerabilities in GitHub Actions Hi! [Runner Guard](https://github.com/Vigilant-LLC/runner-guard), an open-source CI/CD security scanner by [Vigilant Cyber Security](https://www.vigilantdefense.com), identified secu\u2026",
+    "changed_files": 20,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 0,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45010",
+    "created_at": "2026-03-26T06:19:29Z",
+    "deletions": 71,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45010/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45010",
+    "labels": [],
+    "merged": false,
+    "number": 45010,
+    "review_comments_count": 0,
+    "state": "open",
+    "title": "fix: pin 69 unpinned action(s),extract 2 unsafe expression(s) to env vars",
+    "updated_at": "2026-03-26T06:19:29Z"
+  },
+  {
+    "additions": 319,
+    "author": "tarekziade",
+    "author_association": "MEMBER",
+    "body_excerpt": "# What does this PR do? This patch improves the docstring checker implementation (redundant AST walks) and adds cache. For the AST calls, 2.3x speedup check_docstrings.py --check_all on my M1: - before : 29.3s - after: 12.6s",
+    "changed_files": 2,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 1,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45009",
+    "created_at": "2026-03-26T05:31:41Z",
+    "deletions": 43,
+    "draft": false,
+    "files_url": "https://github.com/huggingface/transformers/pull/45009/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45009",
+    "labels": [],
+    "merged": false,
+    "number": 45009,
+    "review_comments_count": 12,
+    "state": "open",
+    "title": "refactor: speed up docstring checker",
+    "updated_at": "2026-03-26T10:10:44Z"
+  },
+  {
+    "additions": 382,
+    "author": "Krishnachaitanyakc",
+    "author_association": "CONTRIBUTOR",
+    "body_excerpt": "## Summary Fix type annotation bugs across config classes that cause `@strict` validation errors from `huggingface_hub`. ### Bool fields mistyped as `int` (22 fixes) Fields with boolean defaults (`True`/`False`) were annotated as `int` ins\u2026",
+    "changed_files": 198,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 1,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45007",
+    "created_at": "2026-03-25T23:12:53Z",
+    "deletions": 382,
+    "draft": true,
+    "files_url": "https://github.com/huggingface/transformers/pull/45007/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45007",
+    "labels": [],
+    "merged": false,
+    "number": 45007,
+    "review_comments_count": 0,
+    "state": "open",
+    "title": "fix: correct type annotations across config classes for @strict validation",
+    "updated_at": "2026-03-25T23:14:00Z"
+  },
+  {
+    "additions": 3,
+    "author": "Krishnachaitanyakc",
+    "author_association": "CONTRIBUTOR",
+    "body_excerpt": "## Summary Fixes #44869 Adds a bounds check in `_split_tokens_on_unicode()` in `tokenization_whisper.py` to handle trailing Unicode replacement characters (U+FFFD) at the end of decoded token streams without crashing with `IndexError`. ##\u2026",
+    "changed_files": 1,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 1,
+    "conversation_url": "https://github.com/huggingface/transformers/pull/45006",
+    "created_at": "2026-03-25T23:03:00Z",
+    "deletions": 1,
+    "draft": true,
+    "files_url": "https://github.com/huggingface/transformers/pull/45006/files",
+    "html_url": "https://github.com/huggingface/transformers/pull/45006",
+    "labels": [],
+    "merged": false,
+    "number": 45006,
+    "review_comments_count": 0,
+    "state": "open",
+    "title": "fix: prevent IndexError in Whisper timestamp decode on trailing replacement char",
+    "updated_at": "2026-03-25T23:05:18Z"
+  },
+  {
+    "additions": 8,
+    "author": "harshaljanjani",
+    "author_association": "CONTRIBUTOR",
+    "body_excerpt": "### What does this PR do? The following failing tests were identified and fixed in this PR (grouped them together since they share related root causes OR the code changes were extremely minimal and didn't warrant separate PRs): \u2192 **Phi-3**\u2026",
+    "changed_files": 2,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/45004",
     "created_at": "2026-03-25T19:58:57Z",
     "deletions": 4,
-    "draft": true,
+    "draft": false,
     "files_url": "https://github.com/huggingface/transformers/pull/45004/files",
     "html_url": "https://github.com/huggingface/transformers/pull/45004",
     "labels": [],
@@ -23,7 +287,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "fix(testing): Fix Parakeet, Evolla, Pi0, and Phi-3 test failures on main CI",
-    "updated_at": "2026-03-25T19:58:57Z"
+    "updated_at": "2026-03-26T05:57:34Z"
   },
   {
     "additions": 1,
@@ -42,28 +306,26 @@
     "files_url": "https://github.com/huggingface/transformers/pull/45002/files",
     "html_url": "https://github.com/huggingface/transformers/pull/45002",
     "labels": [],
-    "merged": false,
+    "merged": true,
     "number": 45002,
     "review_comments_count": 0,
-    "state": "open",
+    "state": "closed",
     "title": "Fix type hint for `attention_chunk_size` in `Llama4TextConfig`",
-    "updated_at": "2026-03-25T17:52:53Z"
+    "updated_at": "2026-03-25T20:42:11Z"
   },
   {
-    "additions": 7,
+    "additions": 17,
     "author": "Sai-Suraj-27",
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? For [torch>=2.10.0](https://docs.pytorch.org/docs/2.10/generated/torch.nn.functional.grouped_mm.html#torch-nn-functional-grouped-mm), the minimum CUDA compute capability requirement for `torch.nn.functional.grouped_\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
-    "comments_count": 2,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 5,
     "conversation_url": "https://github.com/huggingface/transformers/pull/45001",
     "created_at": "2026-03-25T17:00:28Z",
-    "deletions": 0,
+    "deletions": 1,
     "draft": false,
     "files_url": "https://github.com/huggingface/transformers/pull/45001/files",
     "html_url": "https://github.com/huggingface/transformers/pull/45001",
@@ -73,7 +335,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "Add cuda compatibility check for using `grouped_mm`",
-    "updated_at": "2026-03-25T19:31:09Z"
+    "updated_at": "2026-03-26T00:24:20Z"
   },
   {
     "additions": 21,
@@ -108,7 +370,7 @@
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 1,
+    "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44999",
     "created_at": "2026-03-25T16:21:37Z",
     "deletions": 0,
@@ -121,7 +383,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "Add sarvam model",
-    "updated_at": "2026-03-25T16:31:36Z"
+    "updated_at": "2026-03-26T01:38:21Z"
   },
   {
     "additions": 1179,
@@ -148,18 +410,18 @@
     "updated_at": "2026-03-25T14:35:45Z"
   },
   {
-    "additions": 255,
+    "additions": 260,
     "author": "3outeille",
     "author_association": "MEMBER",
     "body_excerpt": "- TODO: - fix failing tests due to API change - make sure our `fsdp2` is not triggered if `accelerate` is on - Introduce `DistributedConfig` - `DistributedConfig(tp_size=2, fsdp_size=2) # plans default to \"auto\"` replaces passing separate\u2026",
-    "changed_files": 7,
+    "changed_files": 9,
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44996",
     "created_at": "2026-03-25T14:20:25Z",
-    "deletions": 216,
+    "deletions": 256,
     "draft": false,
     "files_url": "https://github.com/huggingface/transformers/pull/44996/files",
     "html_url": "https://github.com/huggingface/transformers/pull/44996",
@@ -169,7 +431,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": " from_pretrained distributed refactor (FSDP2 + TP)",
-    "updated_at": "2026-03-25T17:22:04Z"
+    "updated_at": "2026-03-26T10:17:40Z"
   },
   {
     "additions": 3639,
@@ -177,9 +439,11 @@
     "author_association": "MEMBER",
     "body_excerpt": null,
     "changed_files": 8,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43098-11",
+    "cluster_ids": [
+      "cluster-43098-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44994",
     "created_at": "2026-03-25T14:02:50Z",
@@ -196,18 +460,18 @@
     "updated_at": "2026-03-25T14:04:38Z"
   },
   {
-    "additions": 426,
+    "additions": 303,
     "author": "tarekziade",
     "author_association": "MEMBER",
-    "body_excerpt": "# What does this PR do? `make check-repo` can be quite slow, one of the biggest bottleneck is the docstring checker that look at all functions/methods. Checkers in general also don't have any cache to prevent re-running on files that have\u2026",
-    "changed_files": 5,
+    "body_excerpt": "# What does this PR do? `make check-repo` can be quite slow, this patch adds file-level cache to speed up checks. We get up to a 27x speedup - cold cache : 46s - warm cache : 1.6s",
+    "changed_files": 3,
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 3,
+    "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44992",
     "created_at": "2026-03-25T11:40:46Z",
-    "deletions": 62,
+    "deletions": 17,
     "draft": false,
     "files_url": "https://github.com/huggingface/transformers/pull/44992/files",
     "html_url": "https://github.com/huggingface/transformers/pull/44992",
@@ -217,7 +481,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "refactoring: speedup static checks",
-    "updated_at": "2026-03-25T16:52:04Z"
+    "updated_at": "2026-03-26T07:12:21Z"
   },
   {
     "additions": 8,
@@ -276,7 +540,7 @@
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 6,
+    "comments_count": 5,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44988",
     "created_at": "2026-03-25T07:08:20Z",
     "deletions": 2,
@@ -286,10 +550,10 @@
     "labels": [],
     "merged": false,
     "number": 44988,
-    "review_comments_count": 0,
+    "review_comments_count": 1,
     "state": "open",
     "title": "typing: add rule 14 - checks for tie_word_embeddings presence",
-    "updated_at": "2026-03-25T13:00:07Z"
+    "updated_at": "2026-03-26T09:52:02Z"
   },
   {
     "additions": 0,
@@ -364,15 +628,15 @@
     "updated_at": "2026-03-25T17:45:03Z"
   },
   {
-    "additions": 134,
+    "additions": 29,
     "author": "Hyungkeun-Park-Nota",
     "author_association": "FIRST_TIME_CONTRIBUTOR",
-    "body_excerpt": "## What does this PR do? Implements `Mxfp4Dequantize.reverse_op` so that `save_pretrained()` works for GPT-OSS models loaded with `Mxfp4Config(dequantize=True)`. Currently, `Mxfp4Deserialize` has a `reverse_op` (`Mxfp4ReverseDeserialize`),\u2026",
-    "changed_files": 1,
+    "body_excerpt": "## What does this PR do? Fixes `save_pretrained()` failure for GPT-OSS models loaded with `Mxfp4Config(dequantize=True)`. When Triton/kernels are unavailable, transformers automatically falls back to `dequantize=True`, converting MXFP4 wei\u2026",
+    "changed_files": 2,
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 2,
+    "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44983",
     "created_at": "2026-03-25T01:19:59Z",
     "deletions": 0,
@@ -385,7 +649,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "fix: implement Mxfp4Dequantize.reverse_op for save_pretrained support",
-    "updated_at": "2026-03-25T14:09:22Z"
+    "updated_at": "2026-03-26T02:23:28Z"
   },
   {
     "additions": 108,
@@ -409,7 +673,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "Trainer: set skip_logits for loss-only eval when liger enabled",
-    "updated_at": "2026-03-25T02:39:15Z"
+    "updated_at": "2026-03-25T22:07:33Z"
   },
   {
     "additions": 6,
@@ -417,12 +681,10 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "Pre-patch unnecessarily breaks merging a LoRA adapter with a model using CUDA_VISIBLE_DEVICES= e.g. when VRAM is insufficient. It also breaks non-cuda machine operations (such as merging). # What does this PR do? This PR un-breaks `CUDA_VI\u2026",
     "changed_files": 6,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
-    "comments_count": 1,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44980",
     "created_at": "2026-03-24T23:50:07Z",
     "deletions": 6,
@@ -433,20 +695,20 @@
     "merged": false,
     "number": 44980,
     "review_comments_count": 0,
-    "state": "open",
+    "state": "closed",
     "title": "bug-fix: do not assume torch.cuda is available when setting up norm values, even if flash linear attention is available",
-    "updated_at": "2026-03-25T12:33:44Z"
+    "updated_at": "2026-03-25T23:17:21Z"
   },
   {
-    "additions": 218,
+    "additions": 492,
     "author": "michaelbenayoun",
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? Introduces `src/transformers/module_fusion.py`, a utility for fusing adjacent submodules in a model into a single FusedModule that executes them as a chain in one forward pass. The key components are: - `RegistryCol\u2026",
-    "changed_files": 1,
+    "changed_files": 2,
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 1,
+    "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44979",
     "created_at": "2026-03-24T22:33:31Z",
     "deletions": 0,
@@ -459,7 +721,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "Module Fusion API",
-    "updated_at": "2026-03-25T19:55:52Z"
+    "updated_at": "2026-03-25T21:01:32Z"
   },
   {
     "additions": 4,
@@ -688,7 +950,7 @@
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 0,
+    "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44967",
     "created_at": "2026-03-24T11:33:45Z",
     "deletions": 84,
@@ -701,7 +963,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "Fix FA kernel launch needs correct cuda device ctx in multi-gpu env",
-    "updated_at": "2026-03-24T13:49:04Z"
+    "updated_at": "2026-03-26T10:09:41Z"
   },
   {
     "additions": 8,
@@ -733,11 +995,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44965",
     "created_at": "2026-03-24T10:59:31Z",
@@ -759,11 +1019,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes an import in src/transformers/video_processing_utils.py that was causing the main build to fail Fixes # 44933 ## Code Agent Policy The Transformers repo is currently being overwhelmed by a large number of PRs\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44958",
     "created_at": "2026-03-23T20:07:09Z",
@@ -785,11 +1043,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "> **Draft PR \u2014 waiting for issue approval.** This PR is opened alongside the issue request. > It will be marked ready for review after a maintainer gives the go-ahead on the issue. # What does this PR do? Adds native Transformers support f\u2026",
     "changed_files": 12,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44956",
     "created_at": "2026-03-23T19:34:30Z",
@@ -859,11 +1115,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes the non existence of output dictionary change, when parameter output_hidden_states=True is passed to models like CLIP or SigLip. This is especially pertinent for the vision model config. According to #42759 no\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44952",
     "created_at": "2026-03-23T17:02:50Z",
@@ -885,11 +1139,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This pull request adds routing replay functionality for mixture-of-experts (MoE) model types by giving users the option to override router probabilities while processing a forward pass through their models. <!-- Con\u2026",
     "changed_files": 4,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44951",
     "created_at": "2026-03-23T16:29:46Z",
@@ -938,7 +1190,7 @@
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 1,
+    "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44949",
     "created_at": "2026-03-23T16:07:50Z",
     "deletions": 1,
@@ -951,7 +1203,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "Fix: NotebookProgressCallback crash when evaluating with the Trainer",
-    "updated_at": "2026-03-25T07:30:57Z"
+    "updated_at": "2026-03-26T07:25:54Z"
   },
   {
     "additions": 1,
@@ -1175,9 +1427,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes this failing [T5ModelIntegrationTest](https://github.com/huggingface/transformers/actions/runs/23230643883/job/67524758706#step:14:1449) & this [Qwen2IntegrationTest](https://github.com/huggingface/transformer\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43453-9",
+    "cluster_ids": [
+      "cluster-43453-9"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44934",
     "created_at": "2026-03-22T18:03:34Z",
@@ -1321,11 +1575,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? This PR adds a first-class MoE routing capture/replay API for Qwen2Moe and introduces shared MoE routing helpers for reuse by other MoE model families. It adds: - a structured `MoERouting` payload in modeling output\u2026",
     "changed_files": 7,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44925",
     "created_at": "2026-03-22T14:04:40Z",
@@ -1887,11 +2139,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes #43011 `StaticLayer` was missing a `.crop(max_length)` method, so implemented that according to the discussion of the issue. Added `StaticLayer.crop(max_length)` to match the API of StaticCache with the Dynami\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44893",
     "created_at": "2026-03-20T17:48:23Z",
@@ -1937,11 +2187,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? Add a MoERouterHealthCallback to log MoE router-health metrics. <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the\u2026",
     "changed_files": 7,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44891",
     "created_at": "2026-03-20T16:17:05Z",
@@ -2667,11 +2915,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? `Zamba2MambaMixer.__init__` calls `lazy_load_kernel(\"mamba-ssm\")` and `lazy_load_kernel(\"causal-conv1d\")` unconditionally. Models that inherit from it (like NemotronH) and set `use_mamba_kernels=False` in their conf\u2026",
     "changed_files": 3,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44853",
     "created_at": "2026-03-19T10:22:40Z",
@@ -2741,12 +2987,12 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes these failing [Qwen3OmniModelIntegrationTests](https://github.com/huggingface/transformers/actions/runs/23230643883/job/67524756897#step:14:1131) <img width=\"2292\" height=\"161\" alt=\"image\" src=\"https://github.\u2026",
     "changed_files": 3,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43453-9",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43453-9"
     ],
     "cluster_role": "member",
-    "comments_count": 19,
+    "comments_count": 23,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44848",
     "created_at": "2026-03-19T07:30:39Z",
     "deletions": 14,
@@ -2759,13 +3005,13 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "Fix failing `Qwen3OmniModelIntegrationTests`",
-    "updated_at": "2026-03-25T14:57:44Z"
+    "updated_at": "2026-03-26T07:17:55Z"
   },
   {
-    "additions": 72,
+    "additions": 68,
     "author": "tarekziade",
     "author_association": "MEMBER",
-    "body_excerpt": "# What does this PR do? Activated `anti-slop` action. - min-account-age: 30 (most slop accounts are < 1 month old) - detect-spam-usernames: true (Catches obvious spam patterns) - min-profile-completeness: 3 (Low bar, but catches bare-bones\u2026",
+    "body_excerpt": "# What does this PR do? Activated `anti-slop` action. Enabled checks: - `min-account-age: 30` to catch brand-new throwaway accounts, which are common in automated spam waves. - `max-daily-forks: 7` to catch accounts that fork many reposito\u2026",
     "changed_files": 1,
     "cluster_id": null,
     "cluster_ids": [],
@@ -2783,7 +3029,7 @@
     "review_comments_count": 3,
     "state": "open",
     "title": "ci: add anti-slop action",
-    "updated_at": "2026-03-25T16:24:33Z"
+    "updated_at": "2026-03-26T09:21:55Z"
   },
   {
     "additions": 64,
@@ -2818,7 +3064,7 @@
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 3,
+    "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44845",
     "created_at": "2026-03-19T06:14:54Z",
     "deletions": 5,
@@ -2831,7 +3077,7 @@
     "review_comments_count": 1,
     "state": "open",
     "title": "Fix Mllama torch.compile failure caused by new attention mask logic",
-    "updated_at": "2026-03-25T14:28:23Z"
+    "updated_at": "2026-03-26T01:10:06Z"
   },
   {
     "additions": 8468,
@@ -2961,11 +3207,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Pass cu_seqlens derived from packed attention masks to FLA's ShortConvolution and chunk_gated_delta_rule kernels, preventing recurrent state from leaking across sequence boundaries during packed-sequence training. F\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44836",
     "created_at": "2026-03-18T20:24:58Z",
@@ -3059,11 +3303,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 4,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44832",
     "created_at": "2026-03-18T15:33:15Z",
@@ -3435,11 +3677,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 6,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44815",
     "created_at": "2026-03-18T09:54:18Z",
@@ -3559,9 +3799,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": null,
     "changed_files": 31,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43098-11",
+    "cluster_ids": [
+      "cluster-43098-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 12,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44808",
     "created_at": "2026-03-18T04:29:07Z",
@@ -4099,11 +4341,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Some model repos provide `extra_special_tokens` as a list in their tokenizer_config.json, which caused an `AttributeError: 'list' object has no attribute 'keys'`. This converts list inputs to a dict mapping each tok\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44781",
     "created_at": "2026-03-17T04:59:02Z",
@@ -4117,7 +4357,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "Fix `_set_model_specific_special_tokens` to accept list-format `extra_special_tokens`",
-    "updated_at": "2026-03-23T17:18:37Z"
+    "updated_at": "2026-03-26T05:56:54Z"
   },
   {
     "additions": 145,
@@ -4465,11 +4705,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? Adds support for MLP mixers, used by [nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16). Previously, it would crash because it would not recognize the `-` char in t\u2026",
     "changed_files": 3,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44763",
     "created_at": "2026-03-16T17:04:36Z",
@@ -4766,7 +5004,7 @@
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 10,
+    "comments_count": 11,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44739",
     "created_at": "2026-03-16T07:15:33Z",
     "deletions": 7,
@@ -4779,7 +5017,7 @@
     "review_comments_count": 12,
     "state": "open",
     "title": "fix series of failed test case for janus model",
-    "updated_at": "2026-03-18T14:39:24Z"
+    "updated_at": "2026-03-25T20:26:39Z"
   },
   {
     "additions": 6,
@@ -4909,11 +5147,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? This PR introduces a helper utility function, `int_div_ceil`, which performs `math.ceil(a / b)` for non-negative integer operands. This is necessary as the current approach is both error-prone and imprecise (especia\u2026",
     "changed_files": 58,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44729",
     "created_at": "2026-03-15T20:29:38Z",
@@ -5061,9 +5297,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? Migrates the GPT-J model to use the new `@capture_outputs` and `@can_return_tuple` decorators for standardized output collection, as described in #43979. ### Changes - Added `_can_record_outputs` to `GPTJPreTrained\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 2,
@@ -5159,11 +5395,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "Applies the output tracing refactor to ColQwen2ForRetrieval as part of the broader effort tracked in issue #43979 to modernize output handling across all models in the library. Changes in both modular_colqwen2.py and modeling_colqwen2.py:\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44713",
     "created_at": "2026-03-14T20:20:14Z",
@@ -5507,11 +5741,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "### What does this PR do? The following failing tests were identified and fixed in this PR: \u2192 **Kyutai Speech-To-Text**: [The PR [processors] Unbloating simple processors](https://github.com/huggingface/transformers/pull/40377), [refactore\u2026",
     "changed_files": 3,
-    "cluster_id": "cluster-44695-2",
-    "cluster_ids": [
-      "cluster-44695-2"
-    ],
-    "cluster_role": "canonical",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44695",
     "created_at": "2026-03-14T09:05:35Z",
@@ -5807,11 +6039,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "Problem: - On macOS ARM64 + Python 3.13 + transformers 5.x, GPT-2 model's lm_head forward pass produces NaN/Inf values during inference - Root cause: lm_head.weight is tied to transformer.wte.weight, and the shared memory reference causes\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44676",
     "created_at": "2026-03-13T16:28:01Z",
@@ -6099,11 +6329,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR supports PenguinVL model. Paper: https://arxiv.org/abs/2603.06569 Github repo: https://github.com/tencent-ailab/Penguin-VL HuggingFace Model: https://huggingface.co/collections/tencent/ai-lab ## Before submi\u2026",
     "changed_files": 20,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 7,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44662",
     "created_at": "2026-03-13T13:02:26Z",
@@ -6125,11 +6353,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes #44637 This PR makes the PEFT `load_best_model_at_end` path in `Trainer` use a CPU-first adapter reload path during best-model loading. Previously, when training a PEFT model, `Trainer` could reload the best a\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44660",
     "created_at": "2026-03-13T12:59:25Z",
@@ -6199,9 +6425,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@ArthurZucker @Cyrilvallez pls help review. Thx!",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "member",
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44657",
     "created_at": "2026-03-13T10:25:07Z",
@@ -6468,7 +6696,7 @@
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 3,
+    "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44645",
     "created_at": "2026-03-13T02:53:31Z",
     "deletions": 2,
@@ -6481,7 +6709,7 @@
     "review_comments_count": 0,
     "state": "open",
     "title": "fix Image.open failure in case \"tests/models/prompt_depth_anything/te\u2026",
-    "updated_at": "2026-03-13T09:54:51Z"
+    "updated_at": "2026-03-26T09:59:37Z"
   },
   {
     "additions": 2,
@@ -6492,7 +6720,7 @@
     "cluster_id": null,
     "cluster_ids": [],
     "cluster_role": null,
-    "comments_count": 1,
+    "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44644",
     "created_at": "2026-03-13T02:02:45Z",
     "deletions": 1,
@@ -6505,7 +6733,7 @@
     "review_comments_count": 6,
     "state": "open",
     "title": "fix tests/quantization/fp_quant_integration/test_fp_quant.py::FPQuant\u2026",
-    "updated_at": "2026-03-17T08:13:00Z"
+    "updated_at": "2026-03-26T05:58:40Z"
   },
   {
     "additions": 5,
@@ -6537,11 +6765,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Issue: A full 4D attention mask of shape `[1, 1, seq_len, seq_len]` is being created during attention, even when not using alibi for positional embeddings. - This occupied extra memory during training. Root Cause: T\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44641",
     "created_at": "2026-03-12T23:01:11Z",
@@ -6659,11 +6885,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Per a conversion with @Cyrilvallez on Slack on how to make Gemma models more compatible with modular inheritance, this PR: * Updates Gemma models to use `nn.parameter.Buffer` instead of a `self.register_buffer()` fo\u2026",
     "changed_files": 32,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44635",
     "created_at": "2026-03-12T14:47:46Z",
@@ -6685,9 +6909,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? As per the title",
     "changed_files": 3,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44053-8",
+    "cluster_ids": [
+      "cluster-44053-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44634",
     "created_at": "2026-03-12T14:04:36Z",
@@ -7049,11 +7275,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Restores `is_torch_fx_available` in `transformers.utils.import_utils` as a backwards-compatibility shim so that Hub models loaded with `trust_remote_code=True` that still import this symbol no longer raise `ImportEr\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44615",
     "created_at": "2026-03-11T22:52:23Z",
@@ -7634,11 +7858,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44587",
     "created_at": "2026-03-11T01:01:18Z",
@@ -7684,11 +7906,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Passes `eps=config.rms_norm_eps` to both `q_a_layernorm` and `kv_a_layernorm` in the DeepseekV3 MLA attention module. Without this, these layernorms default to `eps=1e-5` instead of the config value (`1e-6`), causin\u2026",
     "changed_files": 5,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44585",
     "created_at": "2026-03-11T00:20:54Z",
@@ -7950,9 +8170,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "Fixes #44448",
     "changed_files": 4,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44053-8",
+    "cluster_ids": [
+      "cluster-44053-8"
+    ],
+    "cluster_role": "canonical",
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44571",
     "created_at": "2026-03-10T14:28:22Z",
@@ -8286,11 +8508,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "Improved wording and grammar in the Auto Classes documentation to enhance readability without changing functionality. # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, you\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44550",
     "created_at": "2026-03-09T16:12:59Z",
@@ -8456,9 +8676,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? As per the title",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44053-8",
+    "cluster_ids": [
+      "cluster-44053-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44542",
     "created_at": "2026-03-09T10:00:29Z",
@@ -8720,9 +8942,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes these failing [MusicgenStereoIntegrationTests](https://github.com/huggingface/transformers/actions/runs/22606636929/job/65500451700#step:14:7870) ## Before submitting - [ ] This PR fixes a typo or improves the\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43453-9",
+    "cluster_ids": [
+      "cluster-43453-9"
+    ],
+    "cluster_role": "canonical",
     "comments_count": 8,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44527",
     "created_at": "2026-03-08T14:26:02Z",
@@ -8866,9 +9090,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes these failing [MarianIntegrationTests](https://github.com/huggingface/transformers/actions/runs/22606636929/job/65500458014#step:14:6186) <img width=\"2378\" height=\"657\" alt=\"image\" src=\"https://github.com/user\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43453-9",
+    "cluster_ids": [
+      "cluster-43453-9"
+    ],
+    "cluster_role": "member",
     "comments_count": 5,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44519",
     "created_at": "2026-03-07T19:53:23Z",
@@ -8914,11 +9140,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? Adds Qwen3-TTS, a series of text-to-speech models by the Qwen team (Alibaba Group), to Transformers. **Architecture:** - `Qwen3TTSForConditionalGeneration` \u2014 text to multi-codebook speech codes (talker) - `Qwen3TTS\u2026",
     "changed_files": 16,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44517",
     "created_at": "2026-03-07T18:48:04Z",
@@ -8967,9 +9191,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes this failing [GPTNeoModelLanguageGenerationTest](https://github.com/huggingface/transformers/actions/runs/22606636929/job/65500455894#step:14:1483) <img width=\"2363\" height=\"239\" alt=\"image\" src=\"https://githu\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43453-9",
+    "cluster_ids": [
+      "cluster-43453-9"
+    ],
+    "cluster_role": "member",
     "comments_count": 5,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44515",
     "created_at": "2026-03-07T18:16:35Z",
@@ -9427,9 +9653,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@ArthurZucker @Cyrilvallez pls help review, thx! This PR fixes failed test case: `pytest -rA tests/models/eurobert/test_modeling_eurobert.py::EuroBertModelTest::test_model_parallelism`",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44490",
     "created_at": "2026-03-06T10:56:48Z",
@@ -9985,9 +10213,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes this failing [DepthProModelIntegrationTest](https://github.com/huggingface/transformers/actions/runs/22606636929/job/65500453624#step:14:4893). <img width=\"2231\" height=\"99\" alt=\"image\" src=\"https://github.com\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43453-9",
+    "cluster_ids": [
+      "cluster-43453-9"
+    ],
+    "cluster_role": "member",
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44456",
     "created_at": "2026-03-05T06:01:06Z",
@@ -10033,9 +10263,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "## Summary - Fixes the `_init_weights` method in `PegasusPreTrainedModel` and `MarianPreTrainedModel` to handle sinusoidal position embeddings before calling `super()._init_weights(module)`, preventing the generic `nn.Embedding` branch fro\u2026",
     "changed_files": 3,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44053-8",
+    "cluster_ids": [
+      "cluster-44053-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44454",
     "created_at": "2026-03-05T03:51:38Z",
@@ -10155,11 +10387,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR adds support for the forthcoming Granite Docling model based on the Granite 4 LLM architecture (`GraniteMoeHybrid`). ## Draft Status This PR is in draft pending the possibility of some additional changes: -\u2026",
     "changed_files": 8,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44445",
     "created_at": "2026-03-04T20:54:17Z",
@@ -10255,9 +10485,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes this failing [ProphetNetModelIntegrationTest](https://github.com/huggingface/transformers/actions/runs/22606636929/job/65500453490#step:14:2331). <img width=\"2303\" height=\"165\" alt=\"image\" src=\"https://github.\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43453-9",
+    "cluster_ids": [
+      "cluster-43453-9"
+    ],
+    "cluster_role": "member",
     "comments_count": 6,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44439",
     "created_at": "2026-03-04T16:55:50Z",
@@ -10460,10 +10692,10 @@
     "labels": [],
     "merged": false,
     "number": 44431,
-    "review_comments_count": 17,
+    "review_comments_count": 49,
     "state": "open",
     "title": "Refactor CLIP-like models",
-    "updated_at": "2026-03-24T13:57:30Z"
+    "updated_at": "2026-03-25T21:26:08Z"
   },
   {
     "additions": 0,
@@ -10811,9 +11043,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? As per the title.",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44053-8",
+    "cluster_ids": [
+      "cluster-44053-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44413",
     "created_at": "2026-03-03T16:24:43Z",
@@ -10883,11 +11117,9 @@
     "author_association": "FIRST_TIMER",
     "body_excerpt": "# What does this PR do? This PR allows the Granite-speech model to use hidden states from the encoder hidden layers. This is an internal model option that is required for the next generation of Granite-speech models. ## Changes: - New conf\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44408",
     "created_at": "2026-03-03T07:50:39Z",
@@ -11103,9 +11335,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? As per the title!",
     "changed_files": 6,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44053-8",
+    "cluster_ids": [
+      "cluster-44053-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44395",
     "created_at": "2026-03-02T14:52:12Z",
@@ -12119,11 +12353,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "### What does this PR do? \u2192 This PR adds **DEIMv2** to Transformers! \u2192 **IMP:** I've linked two notebooks: a [Colab notebook here](https://colab.research.google.com/drive/1jCNefxrKiHWdBEIYTcU3jsd9xyWDwIxC?usp=sharing) demonstrating the fun\u2026",
     "changed_files": 16,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "canonical",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 14,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44339",
     "created_at": "2026-02-27T18:08:53Z",
@@ -12489,9 +12721,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@vasqu This PR skipped 2 invalid test cases: ``` tests/models/voxtral_realtime/test_modeling_voxtral_realtime.py::VoxtralRealtimeForConditionalGenerationModelTest::test_generate_with_quant_cache tests/models/voxtral_realtime/test_modeling_\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44321",
     "created_at": "2026-02-27T09:54:14Z",
@@ -12639,12 +12873,10 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Hello, Transformers team! I submitted a PR to add naver-hyperclovax/HyperCLOVAX-SEED-Think-32B (hereafter HCX), developed by the Korean IT company Naver while executing the government's national AI model project. Th\u2026",
     "changed_files": 17,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
-    "comments_count": 14,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 13,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44314",
     "created_at": "2026-02-27T02:01:28Z",
     "deletions": 6,
@@ -12657,7 +12889,7 @@
     "review_comments_count": 74,
     "state": "open",
     "title": "add HyperClovaX Vision",
-    "updated_at": "2026-03-24T14:27:18Z"
+    "updated_at": "2026-03-26T07:05:48Z"
   },
   {
     "additions": 4,
@@ -13671,11 +13903,9 @@
     "author_association": "COLLABORATOR",
     "body_excerpt": "# What does this PR do? This PR supersedes #43985 to replace the dataset/sampler/dataloader with a data producer that should allow us to more easily get to the next step of async training for RL. <!-- Congratulations! You've made it this f\u2026",
     "changed_files": 6,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44259",
     "created_at": "2026-02-24T15:01:56Z",
@@ -13721,11 +13951,9 @@
     "author_association": "COLLABORATOR",
     "body_excerpt": "# What does this PR do? When post training using context parallelism, some processes may have their chunk of the sample input masked out leading to a NaN loss for that process. Using `nanmean` allows us to keep the real loss that isn't `Na\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44257",
     "created_at": "2026-02-24T14:56:42Z",
@@ -14255,11 +14483,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44228",
     "created_at": "2026-02-23T15:09:05Z",
@@ -14497,11 +14723,9 @@
     "author_association": "FIRST_TIMER",
     "body_excerpt": "# What does this PR do? Add sequence classification capabilities to the family of Granite models (Granite, GraniteMoe, GraniteMoeHybrid, and GraniteMoeShared). Fixes #44214, #35720 ## Why The Granite models currently only have the base mod\u2026",
     "changed_files": 17,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44215",
     "created_at": "2026-02-22T23:24:43Z",
@@ -14815,9 +15039,11 @@
     "author_association": "NONE",
     "body_excerpt": "Fixes #43975 ## Summary This PR fixes: `deepseek-ai/deepseek-coder-6.7b-instruct` incorrectly detokenizes in v5 ## Changes ``` src/transformers/tokenization_utils_tokenizers.py | 12 ++++- tests/models/llama/test_tokenization_llama.py | 60\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44191-8",
+    "cluster_ids": [
+      "cluster-44191-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44198",
     "created_at": "2026-02-21T04:54:47Z",
@@ -14841,9 +15067,11 @@
     "author_association": "NONE",
     "body_excerpt": "Fixes #43937 ## Summary This PR fixes: [GLM-5] ValueError: GenerationConfig is invalid ## Changes ``` src/transformers/generation/configuration_utils.py | 13 +++++++++++- src/transformers/modeling_utils.py | 2 +- tests/generation/test_conf\u2026",
     "changed_files": 3,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44191-8",
+    "cluster_ids": [
+      "cluster-44191-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44197",
     "created_at": "2026-02-21T04:47:32Z",
@@ -14865,9 +15093,11 @@
     "author_association": "NONE",
     "body_excerpt": "Fixes #43881 ## Summary This PR fixes: glm-4v-9b loading failed ## Changes ``` src/transformers/configuration_utils.py | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) ``` ## Testing Please review the changes carefully. T\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44191-8",
+    "cluster_ids": [
+      "cluster-44191-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44196",
     "created_at": "2026-02-21T04:41:02Z",
@@ -14891,9 +15121,11 @@
     "author_association": "NONE",
     "body_excerpt": "Fixes #44062 ## Summary This PR fixes: TypeError: tokenizers.AddedToken() got multiple values for keyword argument 'special' ## Changes ``` src/transformers/tokenization_utils_base.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44191-8",
+    "cluster_ids": [
+      "cluster-44191-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44195",
     "created_at": "2026-02-21T04:38:14Z",
@@ -14917,9 +15149,11 @@
     "author_association": "NONE",
     "body_excerpt": "Fixes #44075 ## Summary This PR fixes: Optimizer SGD args are not used ## Changes ``` src/transformers/trainer_optimizer.py | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) ``` ## Testing Please review the changes carefully. The fix\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44191-8",
+    "cluster_ids": [
+      "cluster-44191-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44194",
     "created_at": "2026-02-21T04:35:53Z",
@@ -14943,9 +15177,11 @@
     "author_association": "NONE",
     "body_excerpt": "Fixes #43986 ## Summary This PR fixes: Confusing crash when loading a video model through AutoProcessor without torchvision installed ## Changes ``` src/transformers/models/auto/video_processing_auto.py | 2 ++ 1 file changed, 2 insertions(\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44191-8",
+    "cluster_ids": [
+      "cluster-44191-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44193",
     "created_at": "2026-02-21T04:34:37Z",
@@ -14969,9 +15205,11 @@
     "author_association": "NONE",
     "body_excerpt": "Fixes #44079 ## Summary This PR fixes: `ModelOutput` keys aren't correctly assigned if key was previously None ## Changes ``` src/transformers/utils/generic.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) ``` ## Testing Please r\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44191-8",
+    "cluster_ids": [
+      "cluster-44191-8"
+    ],
+    "cluster_role": "canonical",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44192",
     "created_at": "2026-02-21T04:33:52Z",
@@ -14995,9 +15233,11 @@
     "author_association": "NONE",
     "body_excerpt": "Fixes #44155 ## Summary This PR fixes: [AudioFlamingo3] Batched inference produces incorrect results due to embedding/token leak between tracks ## Changes ``` .../audioflamingo3/modeling_audioflamingo3.py | 51 +++++++++++++++++++--- .../au\u2026",
     "changed_files": 3,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44191-8",
+    "cluster_ids": [
+      "cluster-44191-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44191",
     "created_at": "2026-02-21T04:32:30Z",
@@ -15021,11 +15261,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Under fp16_full_eval or bf16_full_eval, still don't move model to device if using another dist train backend. This is causing bugs with FSDP2 + bf16_full_eval. The dist train backend would still be in charge of movi\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44189",
     "created_at": "2026-02-21T00:06:16Z",
@@ -15378,16 +15616,14 @@
     "updated_at": "2026-02-27T09:32:43Z"
   },
   {
-    "additions": 2397,
+    "additions": 2396,
     "author": "lmaksym",
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR adds TDT decoder support for Parakeet ASR models, extending the existing CTC-only implementation. It incorporates the initial TDT integration work from [#41545](https://github.com/huggingface/transformers/pu\u2026",
     "changed_files": 27,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 15,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44171",
     "created_at": "2026-02-20T08:44:46Z",
@@ -15401,10 +15637,10 @@
     ],
     "merged": false,
     "number": 44171,
-    "review_comments_count": 54,
+    "review_comments_count": 64,
     "state": "open",
     "title": "Parakeet tdt",
-    "updated_at": "2026-03-24T20:32:14Z"
+    "updated_at": "2026-03-26T09:05:08Z"
   },
   {
     "additions": 74,
@@ -15532,11 +15768,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "What does this PR do? This PR refactors the LongT5 model to use the @capture_outputs and @can_return_tuple decorators for standardized output handling across the model stack. The refactor removes manual handling of: output_attentions outpu\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44161",
     "created_at": "2026-02-19T20:46:49Z",
@@ -15680,9 +15914,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 1,
@@ -15730,9 +15964,11 @@
     "author_association": "NONE",
     "body_excerpt": "Part of the ongoing effort to migrate models to standardized output collection (ref #43979). Replaces manual output_hidden_states/output_attentions/return_dict handling with @capture_outputs and @can_return_tuple decorators in the BioGPT m\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44151",
     "created_at": "2026-02-19T06:55:43Z",
@@ -15754,9 +15990,11 @@
     "author_association": "NONE",
     "body_excerpt": "Part of the ongoing effort to migrate models to standardized output collection (ref #43979). Replaces manual output_hidden_states/output_attentions/return_dict handling with @capture_outputs and @can_return_tuple decorators in the MPT mode\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44150",
     "created_at": "2026-02-19T06:54:09Z",
@@ -15778,9 +16016,11 @@
     "author_association": "NONE",
     "body_excerpt": "Part of the ongoing effort to migrate models to standardized output collection (ref #43979). Replaces manual output_hidden_states/output_attentions/return_dict handling with @capture_outputs and @can_return_tuple decorators in the CPMAnt m\u2026",
     "changed_files": 4,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44149",
     "created_at": "2026-02-19T06:51:06Z",
@@ -15802,9 +16042,11 @@
     "author_association": "NONE",
     "body_excerpt": "Part of the ongoing effort to migrate models to standardized output collection (ref #43979). Replaces manual output_hidden_states/output_attentions/return_dict handling with @capture_outputs and @can_return_tuple decorators in the Bros mod\u2026",
     "changed_files": 4,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44148",
     "created_at": "2026-02-19T06:46:24Z",
@@ -15826,9 +16068,11 @@
     "author_association": "NONE",
     "body_excerpt": "Part of the ongoing effort to migrate models to standardized output collection (ref #43979). Replaces manual output_hidden_states/output_attentions/return_dict handling with @capture_outputs and @can_return_tuple decorators in the CTRL mod\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44147",
     "created_at": "2026-02-19T06:45:32Z",
@@ -15850,11 +16094,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? When using a step-based evaluation strategy (IntervalStrategy.STEPS), the trainer may skip evaluation at the final step if the last step does not align with eval_steps. This avoids missing the final evaluation while\u2026",
     "changed_files": 4,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 15,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44146",
     "created_at": "2026-02-19T05:29:21Z",
@@ -15868,7 +16110,7 @@
     "review_comments_count": 14,
     "state": "open",
     "title": "Ensure final evaluation runs with step-based evaluation strategy",
-    "updated_at": "2026-03-25T15:02:57Z"
+    "updated_at": "2026-03-25T23:48:43Z"
   },
   {
     "additions": 398,
@@ -15876,11 +16118,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR adds support for sequence packing in the ESM2 model. Currently, the RotaryEmbedding class of the ESM2 model supports BSHD format. This PR makes the RotayEmbedding class aware of the`position_ids` and builds\u2026",
     "changed_files": 8,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 14,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44145",
     "created_at": "2026-02-19T02:58:50Z",
@@ -16070,9 +16310,11 @@
     "author_association": "NONE",
     "body_excerpt": "Migrated from https://github.com/huggingface/transformers/pull/44107 (original account: @fumadari). ## Summary - Replaces manual `output_hidden_states`/`return_dict` resolution in `MraModel` with `@merge_with_config_defaults` and `@capture\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44137",
     "created_at": "2026-02-18T21:14:39Z",
@@ -16094,9 +16336,11 @@
     "author_association": "NONE",
     "body_excerpt": "Migrated from https://github.com/huggingface/transformers/pull/44108 (original account: @fumadari). ## Summary - Adds `@merge_with_config_defaults` and `@capture_outputs` to both `VitDetModel` and `VitDetBackbone`, removing manual `output_\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44136",
     "created_at": "2026-02-18T21:14:35Z",
@@ -16118,9 +16362,11 @@
     "author_association": "NONE",
     "body_excerpt": "Migrated from https://github.com/huggingface/transformers/pull/44109 (original account: @fumadari). ## Summary - Part of #43979 \u2014 refactors `hgnet_v2` to use the `capture_outputs` and `merge_with_config_defaults` decorators - Simplifies `H\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44135",
     "created_at": "2026-02-18T21:14:31Z",
@@ -16142,9 +16388,11 @@
     "author_association": "NONE",
     "body_excerpt": "Migrated from https://github.com/huggingface/transformers/pull/44110 (original account: @fumadari). ## Summary - Part of #43979 \u2014 refactors `tvp` to use the `capture_outputs`, `can_return_tuple`, and `merge_with_config_defaults` decorators\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44134",
     "created_at": "2026-02-18T21:14:27Z",
@@ -16166,9 +16414,11 @@
     "author_association": "NONE",
     "body_excerpt": "Migrated from https://github.com/huggingface/transformers/pull/44111 (original account: @fumadari). ## Summary - Part of #43979 \u2014 refactors `poolformer` to use the `capture_outputs`, `can_return_tuple`, and `merge_with_config_defaults` dec\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44133",
     "created_at": "2026-02-18T21:12:22Z",
@@ -16262,9 +16512,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Refactors SpeechT5 to the standardized output tracing interface. - Adds `@capture_outputs` to base encoder/decoder forwards. - Adds `_can_record_outputs` mappings for hidden states and attentions. - Adds `@can_retur\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 1,
@@ -16283,7 +16533,7 @@
     "updated_at": "2026-02-18T11:25:19Z"
   },
   {
-    "additions": 57,
+    "additions": 59,
     "author": "ArthurZucker",
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? Just makes sure we trigger dev version update",
@@ -16304,7 +16554,7 @@
     "review_comments_count": 4,
     "state": "open",
     "title": "update release workflow",
-    "updated_at": "2026-03-25T13:54:10Z"
+    "updated_at": "2026-03-26T09:48:44Z"
   },
   {
     "additions": 3,
@@ -16630,9 +16880,11 @@
     "author_association": "NONE",
     "body_excerpt": "## Summary - Part of #43979 \u2014 refactors `poolformer` to use the `capture_outputs`, `can_return_tuple`, and `merge_with_config_defaults` decorators - Simplifies `PoolFormerLayer` to return a single tensor instead of a 1-tuple - Simplifies `\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "canonical",
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44111",
     "created_at": "2026-02-17T19:38:02Z",
@@ -16654,9 +16906,11 @@
     "author_association": "NONE",
     "body_excerpt": "## Summary - Part of #43979 \u2014 refactors `tvp` to use the `capture_outputs`, `can_return_tuple`, and `merge_with_config_defaults` decorators - Simplifies `TvpAttention` to always return `(output, attention_probs)` (hooks decide what to capt\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44110",
     "created_at": "2026-02-17T19:32:55Z",
@@ -16678,9 +16932,11 @@
     "author_association": "NONE",
     "body_excerpt": "## Summary - Part of #43979 \u2014 refactors `hgnet_v2` to use the `capture_outputs` and `merge_with_config_defaults` decorators - Simplifies `HGNetV2Encoder` by removing `return_dict` parameter (always returns `BaseModelOutputWithNoAttention`)\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44109",
     "created_at": "2026-02-17T19:23:03Z",
@@ -16702,9 +16958,11 @@
     "author_association": "NONE",
     "body_excerpt": "## Summary - Adds `@merge_with_config_defaults` and `@capture_outputs` to both `VitDetModel` and `VitDetBackbone`, removing manual `output_attentions`/`return_dict` resolution - Adds `_can_record_outputs = {\"attentions\": VitDetAttention}`\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44108",
     "created_at": "2026-02-17T19:15:00Z",
@@ -16726,9 +16984,11 @@
     "author_association": "NONE",
     "body_excerpt": "## Summary - Replaces manual `output_hidden_states`/`return_dict` resolution in `MraModel` with `@merge_with_config_defaults` and `@capture_outputs` decorators - Simplifies `MraEncoder` to a plain loop returning a single tensor, removing `\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44107-10",
+    "cluster_ids": [
+      "cluster-44107-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44107",
     "created_at": "2026-02-17T19:04:42Z",
@@ -17062,9 +17322,11 @@
     "author_association": "NONE",
     "body_excerpt": "## Summary Refactors the DeBERTa model to use the standardized output collection interface with `@capture_outputs` and `@can_return_tuple` decorators. ### Changes - Add `_can_record_outputs` on `DebertaPreTrainedModel` mapping `hidden_stat\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44093",
     "created_at": "2026-02-17T14:15:07Z",
@@ -17109,10 +17371,12 @@
     "author": "ManasVardhan",
     "author_association": "NONE",
     "body_excerpt": "## What does this PR do? Refactors the `swin` model to use the standardized output collection interface (`@capture_outputs` and `@can_return_tuple` decorators), as described in #43979. ### Changes **SwinPreTrainedModel:** - Added `_can_rec\u2026",
-    "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "changed_files": 2,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44091",
     "created_at": "2026-02-17T14:14:56Z",
@@ -17158,9 +17422,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "Fixes #43979 ## Summary Refactor T5 to the standardized output tracing interface. ## Changes - Added `_can_record_outputs` on T5 encoder/decoder stack subclasses. - Added `@capture_outputs` on the base stack forward. - Added `@can_return_t\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44089",
     "created_at": "2026-02-17T11:37:18Z",
@@ -17254,9 +17520,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? Refactors the RemBERT model to use the new output tracing decorators (`@capture_outputs` and `@can_return_tuple`), replacing manual output collection boilerplate. ### Changes: - Added `@capture_outputs` decorator t\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 1,
@@ -17280,9 +17546,11 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? Refactors the GPT-J model to use the new `capture_outputs` and `can_return_tuple` decorators for output tracing, following the same pattern as #44046 (CodeGen). ### Changes: - Added `@capture_outputs` decorator on\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44084",
     "created_at": "2026-02-17T11:08:48Z",
@@ -17424,11 +17692,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR refactors the ImageGPT implementation to adopt the new `@capture_outputs` and `@can_return_tuple` decorators for standardized output collection, as part of https://github.com/huggingface/transformers/issues/\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44076",
     "created_at": "2026-02-17T08:46:55Z",
@@ -17450,11 +17716,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? This PR migrates TextNet to the new standardized output tracing system using the `@capture_outputs` and `@can_return_tuple` decorators. It adds `_can_record_outputs`, applies `@capture_outputs` to `TextNetModel.for\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-44056-3",
-    "cluster_ids": [
-      "cluster-44056-3"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44074",
     "created_at": "2026-02-17T08:23:25Z",
@@ -17476,11 +17740,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? This PR migrates VisualBert to the new standardized output tracing system using the `@capture_outputs` and `@can_return_tuple` decorators. Specifically, this PR: - Adds `_can_record_outputs` to `VisualBertPreTraine\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-44056-3",
-    "cluster_ids": [
-      "cluster-44056-3"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44073",
     "created_at": "2026-02-17T08:16:59Z",
@@ -17502,9 +17764,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# Refactor efficientnet output tracing # What does this PR do? This Pull Request migrates the EfficientNet model to use the standardized @capture_outputs and @can_return_tuple decorators. - Added _can_record_outputs to `EfficientNetPreTrai\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 1,
@@ -17650,9 +17912,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "Migrate GPT-J from manual boilerplate output collection to the new decorator-based output tracing system: - Add `_can_record_outputs` to `GPTJPreTrainedModel` - Add `@capture_outputs` and `@merge_with_config_defaults` to `GPTJModel.forward\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 2,
@@ -17848,11 +18110,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? This PR migrates MPNet to the new standardized output tracing system using the `@capture_outputs` decorator. Specifically, this PR: - Applies `@capture_outputs` to `MPNetModel.forward` - Removes manual accumulation\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-44056-3",
-    "cluster_ids": [
-      "cluster-44056-3"
-    ],
-    "cluster_role": "canonical",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44056",
     "created_at": "2026-02-16T18:27:05Z",
@@ -17922,9 +18182,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do?",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-44053-8",
+    "cluster_ids": [
+      "cluster-44053-8"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44053",
     "created_at": "2026-02-16T17:59:48Z",
@@ -18114,9 +18376,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 1,
@@ -18236,9 +18498,11 @@
     "author_association": "NONE",
     "body_excerpt": "```diff diff --git a/transformers/modeling_utils.py b/transformers/modeling_utils.py index 1234567..8901234 100644 --- a/transformers/modeling_utils.py +++ b/transformers/modeling_utils.py @@ -10,6 +10,7 @@ from transformers import PreTrai\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44039",
     "created_at": "2026-02-16T12:01:26Z",
@@ -18334,9 +18598,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 8,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44034",
     "created_at": "2026-02-16T08:04:20Z",
@@ -18406,9 +18672,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the`dpr` model as per #43979 cc @molbap <img width=\"853\" height=\"323\" alt=\"Screenshot 2026-02-16 at 9 13 30 AM\" src=\"https://github.com/user-attachments/assets/d658f1d0-75e8-4eac-8a12-9aeddf194dde\" />",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44030",
     "created_at": "2026-02-16T03:44:19Z",
@@ -18430,9 +18698,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the`rwkv` model as per #43979 cc @molbap <img width=\"856\" height=\"333\" alt=\"Screenshot 2026-02-16 at 9 06 34 AM\" src=\"https://github.com/user-attachments/assets/9c8c5d41-ffbd-45f6-8b9b-1429bcb14543\" />",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44029",
     "created_at": "2026-02-16T03:37:13Z",
@@ -18454,9 +18724,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the`superpoint` model as per #43979 cc @molbap <img width=\"857\" height=\"334\" alt=\"Screenshot 2026-02-16 at 8 53 43 AM\" src=\"https://github.com/user-attachments/assets/17781b76-743b-4b38-923a-8db3b94ccd01\" />",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44028",
     "created_at": "2026-02-16T03:25:14Z",
@@ -18478,9 +18750,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the `speech_encoder_decoder` model as per #43979 cc @molbap <img width=\"852\" height=\"335\" alt=\"Screenshot 2026-02-16 at 8 44 05 AM\" src=\"https://github.com/user-attachments/assets/ee25c72b-b995-403c-b47b-3e9cbae0d2cc\" />",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44027",
     "created_at": "2026-02-16T03:14:41Z",
@@ -18502,9 +18776,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the`vision_encoder_decoder` model as per #43979 cc @molbap <img width=\"849\" height=\"333\" alt=\"Screenshot 2026-02-16 at 8 28 20 AM\" src=\"https://github.com/user-attachments/assets/9f511a17-947b-46ed-82a8-8bb9bb103f15\" />",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44026",
     "created_at": "2026-02-16T02:59:14Z",
@@ -18526,9 +18802,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the `depth_anything` model as per #43979 cc @molbap <img width=\"840\" height=\"330\" alt=\"Screenshot 2026-02-16 at 8 25 01 AM\" src=\"https://github.com/user-attachments/assets/fe7770be-70cb-4343-accb-7407c6bbb4f8\" />",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "canonical",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44025",
     "created_at": "2026-02-16T02:56:17Z",
@@ -18550,11 +18828,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR refactors the FocalNet implementation to adopt the new `@capture_outputs` and `@can_return_tuple` decorators for standardized output collection, as part of https://github.com/huggingface/transformers/issues/\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44024",
     "created_at": "2026-02-15T23:48:12Z",
@@ -18576,9 +18852,11 @@
     "author_association": "NONE",
     "body_excerpt": "## What does this PR do? Refactors the Nystromformer model to use the new `@capture_outputs` and `@can_return_tuple` decorators for standardized output collection, as part of #43979. ### Changes: - Add `_can_record_outputs` on `Nystromform\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44023",
     "created_at": "2026-02-15T21:53:48Z",
@@ -18600,9 +18878,11 @@
     "author_association": "NONE",
     "body_excerpt": "## What does this PR do? Refactors the ConvBERT model to use the new `@capture_outputs` and `@can_return_tuple` decorators for standardized output collection, as part of #43979. ### Changes: - Move `ConvBertPreTrainedModel` after layer def\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44022",
     "created_at": "2026-02-15T21:49:57Z",
@@ -18648,9 +18928,11 @@
     "author_association": "NONE",
     "body_excerpt": "## Summary Refactors the DeBERTa model to use the standardized output collection interface with `@capture_outputs` and `@can_return_tuple` decorators. ### Changes - Add `_can_record_outputs` on `DebertaPreTrainedModel` mapping `hidden_stat\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44020",
     "created_at": "2026-02-15T21:39:17Z",
@@ -18792,9 +19074,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 1,
@@ -18842,9 +19124,11 @@
     "author_association": "NONE",
     "body_excerpt": "## What does this PR do? Refactors the `swin` model to use the standardized output collection interface (`@capture_outputs` and `@can_return_tuple` decorators), as described in #43979. ### Changes **SwinPreTrainedModel:** - Added `_can_rec\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44011",
     "created_at": "2026-02-15T11:11:02Z",
@@ -18866,9 +19150,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "#43979. Refactors SqueezeBert to the standardized output collection interface: - Adds `_can_record_outputs` in `SqueezeBertPreTrainedModel` - Adds `@capture_outputs` on `SqueezeBertModel.forward` - Adds `@can_return_tuple` on task model fo\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 1,
@@ -18916,9 +19200,11 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "## Summary - refactor `ResNetModel` to use `@capture_outputs` for hidden-state collection - register `_can_record_outputs` on `ResNetPreTrainedModel` with `ResNetStage` - switch `ResNetForImageClassification` and `ResNetBackbone` to `@can_\u2026",
     "changed_files": 3,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44007",
     "created_at": "2026-02-15T07:26:52Z",
@@ -18988,9 +19274,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the `codegen` model as per #43979 cc @molbap <img width=\"843\" height=\"445\" alt=\"Screenshot 2026-02-15 at 5 24 52 AM\" src=\"https://github.com/user-attachments/assets/d5aeb711-96a7-4fd8-af7b-0aeac23eeeb1\" /> 2 tests are bei\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44004",
     "created_at": "2026-02-14T23:56:18Z",
@@ -19036,9 +19324,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the `upernet` model as per #43979 cc @molbap <img width=\"856\" height=\"457\" alt=\"Screenshot 2026-02-15 at 4 51 03 AM\" src=\"https://github.com/user-attachments/assets/5dc478d7-d708-4296-a86b-c3bb252d0325\" />",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44002",
     "created_at": "2026-02-14T23:21:45Z",
@@ -19060,9 +19350,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the`univnet` model as per #43979 cc @molbap <img width=\"848\" height=\"462\" alt=\"Screenshot 2026-02-15 at 4 19 00 AM\" src=\"https://github.com/user-attachments/assets/75848429-b9ff-49b3-a028-645aa67fc2ad\" />",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44001",
     "created_at": "2026-02-14T22:50:39Z",
@@ -19084,9 +19376,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the `vision_text_dual_encoder` model issue as per #43979 cc @molbap <img width=\"876\" height=\"292\" alt=\"Screenshot 2026-02-15 at 4 09 07 AM\" src=\"https://github.com/user-attachments/assets/11147a56-993b-4abc-b07a-ec739a53d\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/44000",
     "created_at": "2026-02-14T22:44:14Z",
@@ -19132,9 +19426,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "This PR refactors the `timm_backbone` model issue as per #43979 cc @molbap <img width=\"856\" height=\"423\" alt=\"Screenshot 2026-02-15 at 4 10 15 AM\" src=\"https://github.com/user-attachments/assets/26237c3e-7b66-4f0d-a8b5-ffad6ee7c673\" />",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43998-11",
+    "cluster_ids": [
+      "cluster-43998-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43998",
     "created_at": "2026-02-14T22:12:30Z",
@@ -19156,9 +19452,11 @@
     "author_association": "FIRST_TIMER",
     "body_excerpt": "# What does this PR do? This PR migrates the **RegNet** model to the standardized output collection interface as part of the ongoing refactoring effort in issue #43979. Specifically: - Adds the `_can_record_outputs` dictionary to `RegNetPr\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43997",
     "created_at": "2026-02-14T19:57:54Z",
@@ -19180,9 +19478,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Refactors FNet and CVT output tracing to use the standardized decorators where appropriate. 1. FNet now uses @capture_outputs with _can_record_outputs to collect hidden states. 2. CVT keeps manual hidden-state colle\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43979-28",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43979-28"
     ],
     "cluster_role": "member",
     "comments_count": 1,
@@ -19206,11 +19504,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Refactors falcon in partial fulfillment of https://github.com/huggingface/transformers/issues/43979 ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's th\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43995",
     "created_at": "2026-02-14T14:39:58Z",
@@ -19400,9 +19696,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43979-28",
+    "cluster_ids": [
+      "cluster-43979-28"
+    ],
+    "cluster_role": "canonical",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43983",
     "created_at": "2026-02-13T17:52:45Z",
@@ -19862,11 +20160,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes a common Python pitfall regarding **mutable default arguments**. In Python, default arguments are evaluated only once at function definition time. If a mutable object (like a `list`) is used as a default, that\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43961",
     "created_at": "2026-02-12T17:31:19Z",
@@ -20324,9 +20620,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@ydshieh This PR fixes failed case: `tests/models/exaone_moe/test_modeling_exaone_moe.py::ExaoneMoeIntegrationTest::test_model_logits`, pls help review, thx!",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43938",
     "created_at": "2026-02-12T09:16:04Z",
@@ -20348,9 +20646,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@ydshieh , pls help review, thx!",
     "changed_files": 3,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "canonical",
     "comments_count": 6,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43936",
     "created_at": "2026-02-12T08:34:03Z",
@@ -20876,11 +21176,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Without this like `AutoTokenizer.from_pretrained(...)` does not create `LlamaTokenizer` object. ## Before submitting - [x] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the ca\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 5,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43911",
     "created_at": "2026-02-11T10:53:54Z",
@@ -20902,9 +21200,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@ydshieh , pls help review, thx!",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43910",
     "created_at": "2026-02-11T09:43:08Z",
@@ -20926,9 +21226,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@ydshieh , pls help review, thx!",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43907",
     "created_at": "2026-02-11T08:30:31Z",
@@ -21314,11 +21616,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR adds support for **Param-2-17B-MoE-A2.4B**, a large-scale Mixture-of-Experts (MoE) causal language model. Param-2-17B-MoE-A2.4B uses a **Hybrid Dense + MoE architecture** with 17B total parameters while acti\u2026",
     "changed_files": 8,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43888",
     "created_at": "2026-02-10T11:02:13Z",
@@ -21388,9 +21688,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 8,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43884",
     "created_at": "2026-02-10T09:55:40Z",
@@ -22042,11 +22344,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? Fixes a `NameError: name 'TypeAdapter' is not defined` error when importing transformers without pydantic installed. ## Problem The `TypeAdapter` class from pydantic was used as a type annotation in `_validate_requ\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-43576-4",
-    "cluster_ids": [
-      "cluster-43576-4"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43842",
     "created_at": "2026-02-08T13:01:19Z",
@@ -22140,11 +22440,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR adds Qwen3-ASR to the Transformers library. Fixes #43837 ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [co\u2026",
     "changed_files": 15,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 17,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43838",
     "created_at": "2026-02-08T12:05:43Z",
@@ -22169,11 +22467,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "Fixes #43824 what i think happened in #43824 is that waltwalt36 did not install the optional dependencies like pydantic, causing this issue. According to the core architecture docs, transformers implements a lazy loading mechanism for impo\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-43576-4",
-    "cluster_ids": [
-      "cluster-43576-4"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43836",
     "created_at": "2026-02-08T11:28:31Z",
@@ -22319,11 +22615,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43826",
     "created_at": "2026-02-08T01:49:06Z",
@@ -22345,11 +22639,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 4,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43823",
     "created_at": "2026-02-07T20:24:42Z",
@@ -22927,9 +23219,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingfa\u2026",
     "changed_files": 20,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43098-11",
+    "cluster_ids": [
+      "cluster-43098-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 6,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43795",
     "created_at": "2026-02-06T11:22:56Z",
@@ -22975,9 +23269,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingfa\u2026",
     "changed_files": 15,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43098-11",
+    "cluster_ids": [
+      "cluster-43098-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 5,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43793",
     "created_at": "2026-02-06T09:34:48Z",
@@ -23241,11 +23537,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# Summary This PR updates `SwanLabCallback` to accept `**kwargs` in its `__init__` method and passes them to `swanlab.init()` during setup. Previously, the SwanLab integration did not expose important initialization arguments like `experim\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43779",
     "created_at": "2026-02-05T20:57:14Z",
@@ -23536,9 +23830,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 19,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43098-11",
+    "cluster_ids": [
+      "cluster-43098-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 14,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43767",
     "created_at": "2026-02-05T13:54:13Z",
@@ -23730,9 +24026,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@ydshieh can you help review? Thx!",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "member",
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43758",
     "created_at": "2026-02-05T08:11:34Z",
@@ -23754,11 +24052,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR avoids a hard failure when loading GGUF models that declare the `gpt-oss` architecture. Currently, such models raise a `ValueError` during GGUF config loading. This change maps `gpt-oss` to the closest suppo\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43757",
     "created_at": "2026-02-05T07:56:19Z",
@@ -23948,11 +24244,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "Title: Remove CompressedLinear support for compressed-tensors > 0.13 Body: ## What does this PR do? Prepares transformers for the removal of `CompressedLinear` from compressed-tensors (v0.14+). Users should now call `model.dequantize()` af\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43747",
     "created_at": "2026-02-04T21:25:10Z",
@@ -24672,9 +24966,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingfa\u2026",
     "changed_files": 16,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43098-11",
+    "cluster_ids": [
+      "cluster-43098-11"
+    ],
+    "cluster_role": "member",
     "comments_count": 11,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43707",
     "created_at": "2026-02-03T13:33:41Z",
@@ -25330,11 +25626,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 4,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43665",
     "created_at": "2026-01-31T21:50:43Z",
@@ -25552,11 +25846,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "## What does this PR do? Fixes #43576 The `transformers env` command was failing with: ``` NameError: name 'TypeAdapter' is not defined ``` ### Root Cause The `Serve` class in `serve.py` uses `TypeAdapter` (from pydantic) as a type annotat\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-43576-4",
-    "cluster_ids": [
-      "cluster-43576-4"
-    ],
-    "cluster_role": "canonical",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 13,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43656",
     "created_at": "2026-01-31T18:54:19Z",
@@ -25602,12 +25894,10 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "### What does this PR do? \u2192 Fixes `test_modeling_big_bird.py::BigBirdModelIntegrationTest::test_fill_mask`. For more details on reproducing the bug, please visit the linked issue! Fixes #43653. ### Before submitting - [ ] This PR fixes a t\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
-    "comments_count": 10,
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
+    "comments_count": 11,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43654",
     "created_at": "2026-01-31T18:31:06Z",
     "deletions": 1,
@@ -25620,7 +25910,7 @@
     "review_comments_count": 7,
     "state": "open",
     "title": "fix(tokenizer): Avert special token property overwrites in batch add_tokens calls",
-    "updated_at": "2026-03-10T19:43:49Z"
+    "updated_at": "2026-03-26T06:33:38Z"
   },
   {
     "additions": 1,
@@ -25676,11 +25966,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 8,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 85,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43649",
     "created_at": "2026-01-31T14:06:38Z",
@@ -26319,9 +26607,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "@SunMarc this PR fixes failed case of `tests/quantization/bnb/test_mixed_int8.py::MixedInt8GPT2Test::test_generate_quality_config` for XPU, pls help review, thx!",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43324-12",
+    "cluster_ids": [
+      "cluster-43324-12"
+    ],
+    "cluster_role": "member",
     "comments_count": 2,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43615",
     "created_at": "2026-01-30T05:17:49Z",
@@ -26535,11 +26825,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? `TokenizersBackend._patch_mistral_regex()` is a Mistral-specific tokenizer patch, but the current implementation may call `huggingface_hub.model_info()` during detection. That triggers an HTTP request to `/api/model\u2026",
     "changed_files": 2,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43603",
     "created_at": "2026-01-29T15:30:56Z",
@@ -27191,9 +27479,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 7,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43563",
     "created_at": "2026-01-28T15:20:22Z",
@@ -27311,9 +27601,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 5,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43558",
     "created_at": "2026-01-28T14:08:17Z",
@@ -27383,9 +27675,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do?",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "canonical",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43555",
     "created_at": "2026-01-28T13:55:17Z",
@@ -27407,9 +27701,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do?",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 0,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43554",
     "created_at": "2026-01-28T13:49:19Z",
@@ -27431,9 +27727,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do?",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43553",
     "created_at": "2026-01-28T13:41:21Z",
@@ -27647,11 +27945,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 22,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43543",
     "created_at": "2026-01-28T04:38:01Z",
@@ -27673,11 +27969,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? This PR fixes a bug in the router implementation of several MoE models (Qwen Moe like models, `Olmoe`, `FlexOlmo`). Previously, the raw `router_logits` were being overwritten by the result of the softmax operation:\u2026",
     "changed_files": 7,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43542",
     "created_at": "2026-01-28T04:07:48Z",
@@ -27870,9 +28164,9 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
     "changed_files": 6,
-    "cluster_id": "cluster-36895-97",
+    "cluster_id": "cluster-43488-10",
     "cluster_ids": [
-      "cluster-36895-97"
+      "cluster-43488-10"
     ],
     "cluster_role": "member",
     "comments_count": 8,
@@ -28352,11 +28646,9 @@
     "author_association": "FIRST_TIME_CONTRIBUTOR",
     "body_excerpt": "- Implement RishAIModel, RishAICausalLM with proper inheritance - Add RishAIConfig with full MoE and attention parameters - Integrate RishAITokenizer with BPE support - 100% test coverage with comprehensive test suite - Compatible with tra\u2026",
     "changed_files": 8,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 3,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43506",
     "created_at": "2026-01-26T19:38:43Z",
@@ -28450,9 +28742,11 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "[don't merge] check bot permission",
     "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 11,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43500",
     "created_at": "2026-01-26T15:12:19Z",
@@ -28498,11 +28792,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Fix backward compatibility issue for tie_weights <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set,\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43498",
     "created_at": "2026-01-26T14:17:56Z",
@@ -28692,9 +28984,11 @@
     "author_association": "MEMBER",
     "body_excerpt": "# What does this PR do? check repo bot, don't merge",
     "changed_files": 3,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
+    "cluster_id": "cluster-43488-10",
+    "cluster_ids": [
+      "cluster-43488-10"
+    ],
+    "cluster_role": "member",
     "comments_count": 6,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43488",
     "created_at": "2026-01-26T10:13:21Z",
@@ -28788,11 +29082,9 @@
     "author_association": "CONTRIBUTOR",
     "body_excerpt": "# What does this PR do? Optimizes timestamp rendering in Ernie 4.5 VL video processing by caching text overlays and using torch alpha blending instead of slow `torch->PIL->torch` conversion for each frame. **Performance improvement:** | Mo\u2026",
     "changed_files": 1,
-    "cluster_id": "cluster-36895-97",
-    "cluster_ids": [
-      "cluster-36895-97"
-    ],
-    "cluster_role": "member",
+    "cluster_id": null,
+    "cluster_ids": [],
+    "cluster_role": null,
     "comments_count": 1,
     "conversation_url": "https://github.com/huggingface/transformers/pull/43484",
     "created_at": "2026-01-26T09:40:50Z",
@@ -28929,153 +29221,5 @@
     "state": "closed",
     "title": "Remove stale TODO comments in UDOP tied weights",
     "updated_at": "2026-01-26T14:36:01Z"
-  },
-  {
-    "additions": 39,
-    "author": "Aakash0440",
-    "author_association": "NONE",
-    "body_excerpt": "When passing a batched tensor (B x T x C x H x W) directly to AutoVideoProcessor, the processor incorrectly adds extra singleton dimensions, returning a tensor of shape: 1 x 1 x B x T x C x H x W instead of the expected: B x T x C x H x W\u2026",
-    "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
-    "comments_count": 1,
-    "conversation_url": "https://github.com/huggingface/transformers/pull/43476",
-    "created_at": "2026-01-25T09:28:44Z",
-    "deletions": 2,
-    "draft": false,
-    "files_url": "https://github.com/huggingface/transformers/pull/43476/files",
-    "html_url": "https://github.com/huggingface/transformers/pull/43476",
-    "labels": [],
-    "merged": false,
-    "number": 43476,
-    "review_comments_count": 0,
-    "state": "closed",
-    "title": "Fix: AutoVideoProcessor returns incorrect shape for batched tensor inputs (#43450)",
-    "updated_at": "2026-01-26T13:22:04Z"
-  },
-  {
-    "additions": 2,
-    "author": "xenova",
-    "author_association": "MEMBER",
-    "body_excerpt": "# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflec\u2026",
-    "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
-    "comments_count": 2,
-    "conversation_url": "https://github.com/huggingface/transformers/pull/43473",
-    "created_at": "2026-01-25T03:31:50Z",
-    "deletions": 2,
-    "draft": false,
-    "files_url": "https://github.com/huggingface/transformers/pull/43473/files",
-    "html_url": "https://github.com/huggingface/transformers/pull/43473",
-    "labels": [],
-    "merged": true,
-    "number": 43473,
-    "review_comments_count": 0,
-    "state": "closed",
-    "title": "Fix Apertus model loading (NotImplementedError: Cannot copy out of meta tensor; no data!)",
-    "updated_at": "2026-02-03T09:50:39Z"
-  },
-  {
-    "additions": 37,
-    "author": "antznette1",
-    "author_association": "FIRST_TIME_CONTRIBUTOR",
-    "body_excerpt": "## Summary Improve the UX of `transformers serve` when serving dependencies are not installed by raising an actionable `ImportError` that lists the missing packages and provides copy/pastable installation commands. ## What changed - Update\u2026",
-    "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
-    "comments_count": 0,
-    "conversation_url": "https://github.com/huggingface/transformers/pull/43471",
-    "created_at": "2026-01-25T01:29:41Z",
-    "deletions": 1,
-    "draft": false,
-    "files_url": "https://github.com/huggingface/transformers/pull/43471/files",
-    "html_url": "https://github.com/huggingface/transformers/pull/43471",
-    "labels": [
-      "Code agent slop"
-    ],
-    "merged": false,
-    "number": 43471,
-    "review_comments_count": 0,
-    "state": "closed",
-    "title": "cli: Improve serve missing dependency error",
-    "updated_at": "2026-01-26T13:52:32Z"
-  },
-  {
-    "additions": 1,
-    "author": "xander1421",
-    "author_association": "NONE",
-    "body_excerpt": "## Summary `MusicgenForConditionalGeneration` inherits from `MusicgenPreTrainedModel` which has `config_class` implicitly set to `MusicgenDecoderConfig` via the type annotation `config: MusicgenDecoderConfig`. However, `MusicgenForConditio\u2026",
-    "changed_files": 1,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
-    "comments_count": 1,
-    "conversation_url": "https://github.com/huggingface/transformers/pull/43470",
-    "created_at": "2026-01-25T00:29:47Z",
-    "deletions": 0,
-    "draft": false,
-    "files_url": "https://github.com/huggingface/transformers/pull/43470/files",
-    "html_url": "https://github.com/huggingface/transformers/pull/43470",
-    "labels": [],
-    "merged": false,
-    "number": 43470,
-    "review_comments_count": 1,
-    "state": "closed",
-    "title": "Fix MusicgenForConditionalGeneration config_class inheritance",
-    "updated_at": "2026-02-10T19:50:23Z"
-  },
-  {
-    "additions": 17,
-    "author": "antznette1",
-    "author_association": "FIRST_TIME_CONTRIBUTOR",
-    "body_excerpt": "## Summary Improve HfArgumentParser boolean UX so `Optional[bool]` arguments can be passed as flags without an explicit value. ## What changed - Updated HfArgumentParser to treat `typing.Optional[bool]` `(Union[bool, None])` the same as `b\u2026",
-    "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
-    "comments_count": 2,
-    "conversation_url": "https://github.com/huggingface/transformers/pull/43469",
-    "created_at": "2026-01-24T23:36:23Z",
-    "deletions": 3,
-    "draft": false,
-    "files_url": "https://github.com/huggingface/transformers/pull/43469/files",
-    "html_url": "https://github.com/huggingface/transformers/pull/43469",
-    "labels": [],
-    "merged": false,
-    "number": 43469,
-    "review_comments_count": 0,
-    "state": "open",
-    "title": "argparser: Allow optional bool flags without values",
-    "updated_at": "2026-01-26T15:29:00Z"
-  },
-  {
-    "additions": 99,
-    "author": "sherlock-488",
-    "author_association": "NONE",
-    "body_excerpt": "Fixes #35532 ### What does this PR do? - Adds `encode()` to `RagTokenizer` by forwarding to `current_tokenizer`. - Adds `patch_token` / `patch_token_id` getters and setters, also forwarding to `current_tokenizer`. - Adds a lightweight regr\u2026",
-    "changed_files": 2,
-    "cluster_id": null,
-    "cluster_ids": [],
-    "cluster_role": null,
-    "comments_count": 2,
-    "conversation_url": "https://github.com/huggingface/transformers/pull/43468",
-    "created_at": "2026-01-24T21:20:28Z",
-    "deletions": 0,
-    "draft": false,
-    "files_url": "https://github.com/huggingface/transformers/pull/43468/files",
-    "html_url": "https://github.com/huggingface/transformers/pull/43468",
-    "labels": [
-      "Code agent slop"
-    ],
-    "merged": false,
-    "number": 43468,
-    "review_comments_count": 0,
-    "state": "closed",
-    "title": "RagTokenizer: add encode and patch_token(_id) forwarding",
-    "updated_at": "2026-03-21T05:45:45Z"
   }
 ]