Upload README.md with huggingface_hub

README.md

@@ -33,7 +33,9 @@ const res = await kev.systemOne({
 |---|---|---|---|---|
 | `kev-0.8b` | `q8f32` | 0.82 GB | `Qwen/Qwen3.5-0.8B-Base` | `jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9` |
 | `kev-0.8b` | `q8` | 0.79 GB | `Qwen/Qwen3.5-0.8B-Base` | `jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9` |
+| `kev-0.8b-vision` | `q8f32` | 1.02 GB | `Qwen/Qwen3.5-0.8B-Base` | `jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9` |
 | `kev-4b` | `q8f32` | 4.67 GB | `Qwen/Qwen3.5-4B-Base` | `jaredpalmer/kev-4b@4bc64c6b4c4881148661ffb823ce21fcfdc79a0e` |
+| `kev-4b-vision` | `q8f32` | 5.34 GB | `Qwen/Qwen3.5-4B-Base` | `jaredpalmer/kev-4b@4bc64c6b4c4881148661ffb823ce21fcfdc79a0e` |
 | `kev-9b` | `q8f32` | 8.83 GB | `Qwen/Qwen3.5-9B-Base` | `jaredpalmer/kev-9b@442e597d71840506c326c8c2f5eedd42aeac7bbd` |
 
 Every bundle is int8 weights with fp32 activations, split into 32 MB files so any CDN or proxy can serve them.
@@ -43,10 +45,12 @@ the original fp32 PyTorch model on a fixture set.
 ## Provenance and licenses
 
 - Models and training: [jaredpalmer/kev](https://github.com/jaredpalmer/kev) (Apache-2.0). Source checkpoints:
-  `jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9`, `jaredpalmer/kev-4b@4bc64c6b4c4881148661ffb823ce21fcfdc79a0e`, `jaredpalmer/kev-9b@442e597d71840506c326c8c2f5eedd42aeac7bbd`.
+  `jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9`, `jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9`, `jaredpalmer/kev-4b@4bc64c6b4c4881148661ffb823ce21fcfdc79a0e`, `jaredpalmer/kev-4b@4bc64c6b4c4881148661ffb823ce21fcfdc79a0e`, `jaredpalmer/kev-9b@442e597d71840506c326c8c2f5eedd42aeac7bbd`.
 - Base models: [Qwen3.5](https://huggingface.co/Qwen) (Apache-2.0).
 - Architecture described in [Jev's Architecture Unmasked](https://archerhume.com/posts/jevs-architecture-unmasked).
   The API shapes follow [TypeSafe's System One](https://docs.typesafe.ai/api); Jev is TypeSafe's hosted model and is
   not affiliated with this repo.
 - Conversion: LoRA merged in fp32, exported with the onnxruntime-genai model builder without the LM head, embeddings
   quantized to int8 per row. Details in the [kev.js README](https://github.com/ai-ecoverse/kev.js#readme).
+- `-vision` folders: the same decoder with an `image_embeds` input, plus the base model's own Qwen3.5 vision tower and
+  patch merger (fp16 weights), unmodified and not trained with Kev. Accuracy on images is in the kev.js README.