Add EXAONE 4.5 implementations by nuxlear · Pull Request #45471 · huggingface/transformers

nuxlear · 2026-04-16T08:52:35Z

What does this PR do?

Add EXAONE 4.5 architecture for the EXAONE 4.5 model released by LG AI Research.

This PR adds the modeling code for EXAONE 4.5, which uses the same LLM architecture as EXAONE 4.
Documentation will be updated.

Code Agent Policy

The Transformers repo is currently being overwhelmed by a large number of PRs and issue comments written by
code agents. We are currently bottlenecked by our ability to review and respond to them. As a result,
we ask that new users do not submit pure code agent PRs at this time.
You may use code agents in drafting or to help you diagnose issues. We'd also ask autonomous "OpenClaw"-like agents
not to open any PRs or issues for the moment.

PRs that appear to be fully agent-written will probably be closed without review, and we may block users who do this
repeatedly or maliciously.

This is a rapidly-evolving situation that's causing significant shockwaves in the open-source community. As a result,
this policy is likely to be updated regularly in the near future. For more information, please read CONTRIBUTING.md.

I confirm that this is not a pure code agent PR.

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,
Pull Request section?
Was this discussed/approved via a Github issue or the forum? Please add a link
to it if that's the case.
Did you make sure to update the documentation with your changes? Here are the
documentation guidelines, and
here are tips on formatting docstrings.
Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@zucchini-nlp

zucchini-nlp

Hey @nuxlear , great addition!

I am seeing that the model is almost Qwen2-5VLVision + ExaoneLM with a small difference on the number of kv groups. Can you confirm if official ckpt have different values or if we can drop it, and fully copy from qwen?

If we can drop it, I left comment on how to clean it up further :)

Ah, and also, I see the doc page is missing which should be in docs/source/en/model_docs

zucchini-nlp · 2026-04-16T09:19:58Z

+class Exaone4_5_TextConfig(Exaone4Config):
+    model_type = "exaone4_5_text"
+    base_config_key = "text_config"
+    keys_to_ignore_at_inference = ["past_key_values"]


this looks identical, we should be able to load Exaone4Config directly. For ex see how we load "llama" in llava by default

https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/configuration_llava.py

zucchini-nlp · 2026-04-16T09:21:03Z

+from ..qwen2_vl.video_processing_qwen2_vl import Qwen2VLVideoProcessor
+
+
+@strict


all configs have to be strict and also have @autodoctring(checkpoint="my-hub-repo")

zucchini-nlp

Nice work @nuxlear 🤩

I think the PR looks very good and we just need one final clean-up for style, before asing a core maintainer review

Ping me when you're ready and CI is green for model (ignore unrelated CI failures), and I will ask a core maintainer rveiew

zucchini-nlp · 2026-04-21T14:47:25Z

        ("depth_anything", "DepthAnythingConfig"),
        ("depth_pro", "DepthProConfig"),
-        ("detr", "DetrConfig"),
+        ("detr", "MaskFormerDetrConfig"),


was that done manually or after fix-repo 🤔 very weird if automatically, I need to check

can you revert it, looks like a bad rebase

It breaks after fix-repo in my env, so I fixed it manually.

can you revert, CI isn't complaining in main branch, so i suppose it has smth to do with env setups. Can't point exactly what, so let's revert and see

actually, I have an idea why and I see duplicate names in mapping. Though it shouldn't complain and shouldn't block Exaone. In any case, fixing it needs to be a different PR

zucchini-nlp · 2026-04-21T14:58:13Z

+        outputs = self.model(
+            input_ids=input_ids,
+            pixel_values=pixel_values,
+            pixel_values_videos=pixel_values_videos,
+            image_grid_thw=image_grid_thw,
+            video_grid_thw=video_grid_thw,
+            second_per_grid_ts=second_per_grid_ts,
+            position_ids=position_ids,
+            attention_mask=attention_mask,
+            past_key_values=past_key_values,
+            inputs_embeds=inputs_embeds,
+            use_cache=use_cache,
+            **kwargs,
+        )
+
+        hidden_states = outputs.last_hidden_state
+        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
+        logits = self.lm_head(hidden_states[:, slice_indices, :])
+
+        loss = None
+        if labels is not None:


we don't need forward to override a docsring, instead we can return super().forward(**super_kwargs)

We don't use rope_deltas or mm_token_type_ids in forward(), so can we drop these kwargs and use CausalLMOutputWithPast instead of the generated Exaone4_5_CausalLMOutputWithPast? (which has rope_deltas unnecessarily)

Ah I see, indeed, we don't have a way to easily drop args from signature

zucchini-nlp · 2026-04-21T14:59:13Z

+class Exaone4_5_ProcessorKwargs(ProcessingKwargs, total=False):
+    _defaults = {
+        "text_kwargs": {
+            "padding": False,
+        },
+        "videos_kwargs": {"return_metadata": True},
+    }
+
+
+class Exaone4_5_Processor(Qwen2_5_VLProcessor):
+    tokenizer_class = "AutoTokenizer"


nah, I see you added it in processing_auto, so now we can just delete these

are we deleteing it?

If I just delete Exaone4_5_Processor it breaks processing_exaone4_5.py

we delete the file processing.py entirely, It is mapped in auto_processing to qwen,ii think

zucchini-nlp · 2026-04-21T15:03:09Z

You might also need a rebase, and at last run make fix-repo for repo consistency CI

nuxlear · 2026-04-27T10:09:24Z

@zucchini-nlp Sorry for the delay. I'm starting to address the feedback.

BTW, since EXAONE 4.5 was recently released in vLLM (v0.20.0), we need to keep some class names as-is for compatibility, including Exaone4_5_ImageProcessor.

Is there a recommended way to keep the model config unchanged while mapping the old name to the Transformers convention (e.g., Exaone4_5_ImageProcessor → Qwen2VLImageProcessor)?

If not, can I just patch this by aliasing the class name, e.g.,
from transformers import Qwen2VLImageProcessor as Exaone4_5_ImageProcessor in modeling_exaone4_5.py?

zucchini-nlp · 2026-04-27T10:17:40Z

@nuxlear not sure I understand the vLLM part. We didn't yet release the model in transformers, so vLLM should be using its own integration without importing anything like from transformers import Exaone4_5_ImageProcessor

What part do we need to keep without changing?

nuxlear · 2026-04-27T10:47:05Z

Yes, we understand that it would be better for vLLM to use its own integration.

However, in this case, it would require updating our model config (e.g., exaone4_5_text → exaone4, and Exaone4_5_[Image/Video]Processor → Qwen2VL[Image/Video]Processor) and submitting a separate PR to fix the imports in vLLM (see here).

So if there is a simple way to map or alias the existing config values and class names, we’d prefer that. Otherwise, we’d need to update the EXAONE 4.5 config, which would break compatibility with vLLM v0.20.0 and require additional changes.

zucchini-nlp · 2026-04-27T11:02:28Z

@nuxlear so vllm is importing smth that doesn't yet exist and isn't released? 🫠

In that case, I don't think it falls into breaking BC since it wasn't released yet and there is nothing to break. Seems like vLLM can't support Exaone before transformers release anyway

nuxlear · 2026-04-27T11:26:29Z

@zucchini-nlp I understand. Then we will update the model config and open a patch PR later. I'll continue addressing the feedback 😃

nuxlear · 2026-04-29T00:16:41Z

@zucchini-nlp I think it's almost done, but I can't figure out why utils/check_repo.py is failing. It passes in my environment with the latest commit. (Edit: this was my bad. Never mind.)

To get the tests fully passing, we need to update the config from exaone4_5_text to exaone4, which may break the current vLLM job. Could you check the failing tests locally with this change? If it works on your side, we’ll proceed with updating the config and docs accordingly.

zucchini-nlp

Great work, we can request a core maintainer review as last step before merging. I left some nitty-picky comments

Btw, are we deleting the unused processor class?

zucchini-nlp · 2026-04-29T09:49:44Z

+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForImageTextToText.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,


nit: lets delete torch_dtype, we just merged a PR cleaning all docs. It default to dtype from config when loading

zucchini-nlp · 2026-04-29T09:50:17Z

        ("depth_anything", "DepthAnythingConfig"),
        ("depth_pro", "DepthProConfig"),
-        ("detr", "DetrConfig"),
+        ("detr", "MaskFormerDetrConfig"),


can you revert it, looks like a bad rebase

zucchini-nlp · 2026-04-29T09:52:46Z

+        self.num_key_value_groups = self.num_heads // self.num_key_value_heads
+        self.q_dim = self.num_heads * self.head_dim
+        self.kv_dim = self.num_key_value_heads * self.head_dim
+        self.qkv = nn.Linear(self.dim, self.q_dim + (self.kv_dim * 2), bias=True)


i was pointed recently, that we usually prefer unfused qkv, but I will leave it for core maintainer to decide. In any case, you won't have to change state-dicts, we will fuse-unfuse on the fly

Honestly yes, but atp we have adopted too many qwen vl like checkpoints that have it fused. Usually it's easier on TP (unfused) but the vision backbones are small enough that it doesn't matter too much

zucchini-nlp · 2026-04-29T09:53:51Z

+        self,
+        hidden_states: torch.Tensor,
+        cu_seqlens: torch.Tensor,
+        rotary_pos_emb: torch.Tensor | None = None,


nit: unused arg rotary_pos_emb (I realize it is copy from qwen but lets delete)

zucchini-nlp · 2026-04-29T09:55:40Z

+        elif position_ids.ndim > 2:
+            position_ids = position_ids[-1]


is this possible? I think we shouldn't allow it and let it error out naturally at some point

zucchini-nlp · 2026-04-29T09:56:36Z

+        )
+
+
+@auto_docstring(checkpoint="LGAI-EXAONE/EXAONE-4.5-33B")


ultra nit: we don't need to add a ckpt everywhere, only in config classes :)

zucchini-nlp · 2026-04-29T09:56:55Z

+class Exaone4_5_ProcessorKwargs(ProcessingKwargs, total=False):
+    _defaults = {
+        "text_kwargs": {
+            "padding": False,
+        },
+        "videos_kwargs": {"return_metadata": True},
+    }
+
+
+class Exaone4_5_Processor(Qwen2_5_VLProcessor):
+    tokenizer_class = "AutoTokenizer"


are we deleteing it?

zucchini-nlp · 2026-04-29T10:03:42Z

To get the tests fully passing, we need to update the config from exaone4_5_text to exaone4, which may break the current vLLM job. Could you check the failing tests locally with this change? If it works on your side, we’ll proceed with updating the config and docs accordingly.

You mean the configs on the hub? Yes, looking at the tests looks like the changing model-type will fix it. If you cannot change config.json due to BC with vLLM/etc, I recomment to change it directly in code. For ex, smth like this inside a config.__post_init__:

# inlne comment here explaining why we override the model-type
if isinstance(text_config, dict):
    model_type = text_config.get('model_type', 'exaone4')
    if model_type = "exaone4_5_text": model_type = "exaone4"
    text_config = CONFIG_MAPPING[model_type](**text_cofnig)
elif text_config is None:
    text_config = CONFIG_MAPPING['exaone4']()

nuxlear · 2026-04-29T16:51:49Z

failed test: https://app.circleci.com/pipelines/github/huggingface/transformers/173444/workflows/6dec560d-7daf-4af6-bac6-fb9973c822b6/jobs/2292655
We will update the processor configs right after this PR is merged.

HuggingFaceDocBuilderDev · 2026-04-30T08:32:00Z

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

github-actions · 2026-04-30T09:00:07Z

CI Results

Workflow Run ⚙️

Commit Info

Context	Commit	Description
RUN	66a4e642	workflow commit (merge commit)
PR	e83132cb	branch commit (from PR)
main	53b92b94	base commit (on `main`)

Model CI Report

❌ 2 new failed tests from this PR 😭

exaone4_5:
tests/models/exaone4_5/test_modeling_exaone4_5.py::Exaone4_5_IntegrationTest::test_model_generation_image_text (✅ ⟹ ❌)
tests/models/exaone4_5/test_modeling_exaone4_5.py::Exaone4_5_IntegrationTest::test_model_logits (✅ ⟹ ❌)

vasqu · 2026-04-30T16:00:25Z

I will take a look in a bit 🤗

vasqu

Looks already very solid, left some comments but I think it's nothing major overall just smaller details

nuxlear · 2026-04-30T20:01:13Z

@vasqu Thanks for the review! Could you take a final look at the updates?

github-actions · 2026-05-04T12:37:40Z

[For maintainers] Suggested jobs to run (before merge)

run-slow: auto, exaone4_5

vasqu · 2026-05-04T12:40:25Z

run-slow: exaone4_5

vasqu

LGTM, I'm merging shortly just sanity checking with CI 🤗

github-actions · 2026-05-04T12:42:05Z

Workflow Run ⚙️

This comment contains run-slow, running the specified jobs:

models: ["models/exaone4_5"]
quantizations: []

github-actions · 2026-05-04T12:47:14Z

CI Results

Workflow Run ⚙️

Commit Info

Context	Commit	Description
RUN	fe1b87e1	workflow commit (merge commit)
PR	8ff7a555	branch commit (from PR)
main	8c004ec6	base commit (on `main`)

⚠️ No test being reported (jobs are skipped or cancelled)!

vasqu · 2026-05-04T12:52:02Z

run-slow: exaone4_5

github-actions · 2026-05-04T12:53:35Z

Workflow Run ⚙️

This comment contains run-slow, running the specified jobs:

models: ["models/exaone4_5"]
quantizations: []

github-actions · 2026-05-04T13:07:48Z

CI Results

Workflow Run ⚙️

Commit Info

Context	Commit	Description
RUN	2697d317	workflow commit (merge commit)
PR	8fbf33bf	branch commit (from PR)
main	8c004ec6	base commit (on `main`)

✅ No failing test specific to this PR 🎉 👏 !

vasqu · 2026-05-04T13:30:59Z

Nice, gz @nuxlear glad we got this in 🫡

nuxlear · 2026-05-04T13:40:48Z

Finally! Thank you @vasqu and @zucchini-nlp for your help and effort 😄

* Add EXAONE 4.5 modeling & config code * Add test code for EXAONE 4.5 and Fix style * Address PR feedback * Address PR feedback * Update EXAONE 4.5 docs * Update docstring * Address the feedback * Fix docs * Minor fix * Minor fix * Update docs * Address the feedback * Skip failed test * Address the feedback * Minor fix * Revert skipping test * Fix test * Address the feedback * fixup autos, nits, and logits test to CI * fix date * last quick fixes --------- Co-authored-by: LG-AI-EXAONE <exaonemodels@lgresearch.ai> Co-authored-by: vasqu <antonprogamer@gmail.com> Co-authored-by: Anton Vlasjuk <73884904+vasqu@users.noreply.github.com>

@tohtana

# Add EXAONE 4.5 model support for Inference V2 ## Summary Add support for LG AI Research's EXAONE 4.5 language model in DeepSpeed Inference V2. The EXAONE 4.5 text decoder shares EXAONE 4.0's post-norm + QK-Norm parameter layout (`text_config.architectures == ["Exaone4ForCausalLM"]`), so the transformer container and most of the inference model are reused. EXAONE 4.5 is also a hybrid-attention model: `sliding_attention` layers apply llama3-scaled RoPE, and `full_attention` layers use no positional embedding (global NoPE). This implementation follows that reference behavior. ## Changes - New model implementation `deepspeed/inference/v2/model_implementations/exaone4_5/`: - `container.py`: non-transformer container for the multimodal checkpoint layout. The LM weights are nested under `model.language_model.` and `lm_head` stays top-level. - `model.py`: hybrid attention on top of the reused EXAONE 4.0 forward. - `sliding_attention` layers use trained-frequency RoPE with llama3-scaled inverse frequencies. A unit test checks the values against transformers' `ROPE_INIT_FUNCTIONS["llama3"]`. - `full_attention` layers dispatch to a separate NoPE attention module. - Sequence length is capped at `sliding_window` (4096). The dense blocked attention kernel has no local mask, and at or below the window size dense causal attention is equivalent to sliding attention. The cap is enforced in the scheduler path (`get_kv_requirements`) and the direct path (`maybe_allocate_kv`). - `activation_dtype` handles the transformers v5 config (`dtype` vs `torch_dtype`, str vs `torch.dtype`). - `policy.py`: extracts `text_config`, reuses `Exaone4TransformerContainer` under the `model.language_model.layers` prefix, and leaves the vision tower (`model.visual.`) and the MTP head (`mtp.`) unmapped. - `exaone4/model.py`: extracted a behavior-neutral `_forward_attention` seam for the per-layer dispatch, and fixed a latent aliasing crash in `_apply_qk_norm`. For a single-row slice, `contiguous()` returns an alias rather than a copy, so the write-back overlapped its own source and every single-token decode step raised a RuntimeError. The q/k slices are now cloned. This also affected EXAONE 4.0, which had not been exercised on the decode path. - `checkpoint/huggingface_engine.py`: derive `max_seq_length` from the nested `text_config.max_position_embeddings` when the top-level (multimodal) config doesn't have it. - `kernels/ragged_ops/linear_blocked_kv_rotary`: the trained-RoPE path now keeps the inverse frequencies and phase construction in FP32 instead of coupling them to the Q/K activation dtype (repair by @tohtana, merged from [Bias92#1](Bias92#1)). Q/K/V and the KV cache stay FP16/BF16; the rotated outputs are cast back to the activation dtype. A kernel test at position 4095 covers both dtypes. - Registered `exaone4_5` in `engine_factory.py` and `model_implementations/__init__.py`. - Unit tests for the llama3 frequency computation (against transformers), the per-layer attention dispatch, and the sequence-length cap. ## Why the mapping is exact Checked against the real `LGAI-EXAONE/EXAONE-4.5-33B` checkpoint index (1064 tensors). All 64 decoder layers expose exactly the 11 parameters the 4.0 container maps, and every non-language-model tensor falls under `model.visual.` (342) or `mtp.` (15), both declared unmapped. ## Testing Validated on an A100 80GB (SXM4) at `73c325e`, CUDA 12.4, torch 2.4.1+cu124 / transformers 5.13.1, with the real `LGAI-EXAONE/EXAONE-4.5-33B` checkpoint (bf16, shard SHA-256 verified): - Unit tests for the diff-impacted scope, run on CI-matched pytest 8.3.5: rotary kernels 58/58, blocked attention 23/23, EXAONE 4.5 model 6/6. - FP32-phase kernel test at position 4095 passes for both FP16 and BF16. - Load: both shards load and every container initializes (mapping and the `model.visual.`/`mtp.` skip both work). `max_sequence_length` resolves to the enforced 4096 cap and the runtime rope buffer is `torch.float32`. - All pre-commit hooks (including clang-format on the CUDA files) pass on the changed files. - Greedy generation through `engine.put` (single-sequence decode, which exercises the trained-rotary kernel, the NoPE module and the per-layer dispatch): ``` 'The capital of France is' -> ' Paris. \nThe capital of Germany is Berlin. \nThe capital of' '대한민국의 수도는' -> ' 어디인가요?\n서울입니다.\n질문은 대한민국의 수도를 묻고 있으며...' '2 + 2 =' -> ' 4.\n\nBut in the example, they said "the sum of all elements is' 'The opposite of hot is' -> ' cold. \nThe opposite of happy is sad. \nThe opposite of' ``` Note: the direct-put validation used `do_checks=False` because `engine.can_schedule` currently passes `state_manager.free_blocks` (a Python `list`, despite the `torch.Tensor` annotation) into `get_kv_requirements`, which expects an int. That is a pre-existing type mismatch that affects all models on the `put(do_checks=True)` path. MII drives the engine via `query()` + `put(do_checks=False)`, so it never hits it. Happy to file that separately. ## Scope Serves the base autoregressive text path of EXAONE 4.5 (e.g. `LGAI-EXAONE/EXAONE-4.5-33B`, bf16) up to 4096 tokens. Out of scope / follow-ups: - Vision tower (VLM, `Exaone4_5ForConditionalGeneration`) - MTP self-speculative decoding - FP8 / AWQ quantized variants (only fp16/bf16, same as EXAONE 4.0) - Long context (>4096), which needs a local attention mask in the dense blocked attention kernel The merged EXAONE 4.0 implementation has the same uniform-RoPE issue on its `full_attention` layers (plus unscaled llama3 rope). This PR keeps 4.0 behavior unchanged apart from the decode crash fix. I'd like to fix 4.0 in a follow-up PR so the two changes stay independently reviewable. ## Requirements `transformers >= 5.3.0`. EXAONE 4.5 landed in transformers 5.3 (huggingface/transformers#45471). --------- Signed-off-by: Bias92 <pewpewplay315@gmail.com> Signed-off-by: Masahiro Tanaka <mtanaka@anyscale.com> Co-authored-by: Masahiro Tanaka <mtanaka@anyscale.com>

zucchini-nlp reviewed Apr 16, 2026

View reviewed changes

nuxlear force-pushed the add-exaone4_5 branch from 361b242 to 31991e7 Compare April 20, 2026 13:46

nuxlear requested a review from zucchini-nlp April 20, 2026 15:34

zucchini-nlp reviewed Apr 21, 2026

View reviewed changes

nuxlear force-pushed the add-exaone4_5 branch from 31991e7 to 1f23651 Compare April 27, 2026 15:16

lgai-exaone added 9 commits April 29, 2026 03:57

Add EXAONE 4.5 modeling & config code

a7838c9

Add test code for EXAONE 4.5 and Fix style

4afe826

Address PR feedback

4c9c815

Address PR feedback

1923fd9

Update EXAONE 4.5 docs

45ae7ca

Update docstring

4e5f13d

Address the feedback

ec86389

Fix docs

7204958

Minor fix

fa9c371

nuxlear force-pushed the add-exaone4_5 branch from e887ee3 to fa9c371 Compare April 28, 2026 18:58

evalstate mentioned this pull request Apr 28, 2026

Cumulative defect fixes from recent Transformers PRs evalstate/transformers#41

Open

lgai-exaone added 2 commits April 29, 2026 09:58

Minor fix

2f81fdb

Update docs

a8cebd1

nuxlear requested a review from zucchini-nlp April 29, 2026 05:58

zucchini-nlp approved these changes Apr 29, 2026

View reviewed changes

Address the feedback

e88a488

vasqu reviewed Apr 30, 2026

View reviewed changes

Address the feedback

933c074

nuxlear requested a review from vasqu April 30, 2026 20:53

vasqu added the New model label May 4, 2026

vasqu and others added 2 commits May 4, 2026 14:36

fixup autos, nits, and logits test to CI

e296d79

Merge branch 'main' into add-exaone4_5

0597151

fix date

8ff7a55

vasqu approved these changes May 4, 2026

View reviewed changes

last quick fixes

8fbf33b

vasqu enabled auto-merge May 4, 2026 13:07

vasqu added this pull request to the merge queue May 4, 2026

Merged via the queue into huggingface:main with commit a5b83a7 May 4, 2026
29 checks passed

lkm2835 mentioned this pull request May 10, 2026

Fix EXAONE-4.5 to align with Transformers update vllm-project/vllm#42246

Merged

4 tasks

Bias92 mentioned this pull request Jul 5, 2026

Add EXAONE 4.5 model support for Inference V2 deepspeedai/DeepSpeed#8121

Merged

		from ..qwen2_vl.video_processing_qwen2_vl import Qwen2VLVideoProcessor


		@strict

		)


		@auto_docstring(checkpoint="LGAI-EXAONE/EXAONE-4.5-33B")

Uh oh!

Conversation

nuxlear commented Apr 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What does this PR do?

Code Agent Policy

Before submitting

Who can review?

Uh oh!

zucchini-nlp left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

zucchini-nlp left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

zucchini-nlp Apr 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

zucchini-nlp Apr 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

zucchini-nlp commented Apr 21, 2026

Uh oh!

nuxlear commented Apr 27, 2026

Uh oh!

zucchini-nlp commented Apr 27, 2026

Uh oh!

nuxlear commented Apr 27, 2026

Uh oh!

zucchini-nlp commented Apr 27, 2026

Uh oh!

nuxlear commented Apr 27, 2026

Uh oh!

nuxlear commented Apr 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

zucchini-nlp left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

nuxlear commented Apr 16, 2026 •

edited

Loading

zucchini-nlp left a comment •

edited

Loading

zucchini-nlp Apr 29, 2026 •

edited

Loading

zucchini-nlp Apr 29, 2026 •

edited

Loading

nuxlear commented Apr 29, 2026 •

edited

Loading

zucchini-nlp commented Apr 29, 2026 •

edited

Loading