From 5cba6839e6cb8ede0c81947557b76617468d0d61 Mon Sep 17 00:00:00 2001
From: Haoqing Wang <78337154+hqhq1025@users.noreply.github.com>
Date: Mon, 11 May 2026 14:58:22 +0800
Subject: [PATCH] Document MolmoWeb hf_overrides (#42163)
Signed-off-by: Haoqi Wang <78337154+hqhq1025@users.noreply.github.com>
---
docs/models/supported_models.md | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/docs/models/supported_models.md b/docs/models/supported_models.md
index 08f4c2b14b..454ab08deb 100644
--- a/docs/models/supported_models.md
+++ b/docs/models/supported_models.md
@@ -598,7 +598,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
| `MiniMaxVL01ForConditionalGeneration` | MiniMax-VL | T + IE+ | `MiniMaxAI/MiniMax-VL-01`, etc. | | ✅︎ |
| `Mistral3ForConditionalGeneration` | Mistral3 (HF Transformers) | T + I+ | `mistralai/Mistral-Small-3.1-24B-Instruct-2503`, etc. | ✅︎ | ✅︎ |
| `MolmoForCausalLM` | Molmo | T + I+ | `allenai/Molmo-7B-D-0924`, `allenai/Molmo-7B-O-0924`, etc. | ✅︎ | ✅︎ |
-| `Molmo2ForConditionalGeneration` | Molmo2 | T + I+ / V | `allenai/Molmo2-4B`, `allenai/Molmo2-8B`, `allenai/Molmo2-O-7B` | ✅︎ | ✅︎ |
+| `Molmo2ForConditionalGeneration` | Molmo2 | T + I+ / V | `allenai/Molmo2-4B`, `allenai/Molmo2-8B`, `allenai/Molmo2-O-7B`, `allenai/MolmoWeb-4B`^, `allenai/MolmoWeb-8B`^ | ✅︎ | ✅︎ |
| `Moondream3ForCausalLM` | Moondream3 | T + I | `moondream/moondream3-preview` | | ✅︎ |
| `MusicFlamingoForConditionalGeneration` | MusicFlamingo | T + A | `nvidia/music-flamingo-2601-hf`, `nvidia/music-flamingo-think-2601-hf` | ✅︎ | ✅︎ |
| `NVLM_D_Model` | NVLM-D 1.0 | T + I+ | `nvidia/NVLM-D-72B`, etc. | | ✅︎ |
@@ -666,6 +666,11 @@ Some models are supported only via the [Transformers modeling backend](#transfor
!!! note
For `InternVLChatModel`, only InternVL2.5 with Qwen2.5 text backbone (`OpenGVLab/InternVL2.5-1B` etc.), InternVL3 and InternVL3.5 have video inputs support currently.
+!!! note
+ To use `allenai/MolmoWeb-4B` or `allenai/MolmoWeb-8B`, serve the checkpoint
+ with the Molmo2 architecture and disable multimodal-prefix attention:
+ `--hf-overrides '{"architectures": ["Molmo2ForConditionalGeneration"], "is_mm_prefix_lm": false}'`.
+
!!! note
`Moondream3ForCausalLM` uses task-specific prompt templates for `query`
and `caption`. The native `detect` and `point` skills require custom