model card: trim intro
Browse files
README.md
CHANGED
|
@@ -15,8 +15,7 @@ base_model:
|
|
| 15 |
|
| 16 |
**GLM-5.2 with sight.** A vision-language model that bolts the MoonViT vision encoder from
|
| 17 |
[Kimi-K2.6](https://huggingface.co/moonshotai/Kimi-K2.6) onto
|
| 18 |
-
[GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) through a trained PatchMerger projector
|
| 19 |
-
shipped as **one self-contained checkpoint** you can hand straight to SGLang.
|
| 20 |
|
| 21 |
GLM-5.2 is a strong open reasoning model with no vision input. This checkpoint adds it,
|
| 22 |
without touching a single GLM weight: the text backbone and the vision tower are both frozen
|
|
|
|
| 15 |
|
| 16 |
**GLM-5.2 with sight.** A vision-language model that bolts the MoonViT vision encoder from
|
| 17 |
[Kimi-K2.6](https://huggingface.co/moonshotai/Kimi-K2.6) onto
|
| 18 |
+
[GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) through a trained PatchMerger projector.
|
|
|
|
| 19 |
|
| 20 |
GLM-5.2 is a strong open reasoning model with no vision input. This checkpoint adds it,
|
| 21 |
without touching a single GLM weight: the text backbone and the vision tower are both frozen
|