Upload nanoVLM using push_to_hub

config.json

@@ -2,13 +2,13 @@
     "vit_hidden_dim": 768,
     "vit_inter_dim": 3072,
     "vit_patch_size": 16,
-    "vit_img_size": 512,
+    "vit_img_size": 256,
     "vit_n_heads": 12,
     "vit_dropout": 0.0,
     "vit_n_blocks": 12,
     "vit_ln_eps": 1e-06,
     "vit_cls_flag": false,
-    "vit_model_type": "google/siglip2-base-patch16-512",
+    "vit_model_type": "google/siglip2-base-patch16-256",
     "lm_hidden_dim": 960,
     "lm_inter_dim": 2560,
     "lm_rms_eps": 1e-05,
@@ -29,7 +29,7 @@
     "lm_tokenizer": "HuggingFaceTB/SmolLM2-360M-Instruct",
     "lm_chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
     "lm_eos_token_id": 0,
-    "mp_pixel_shuffle_factor": 4,
+    "mp_pixel_shuffle_factor": 2,
     "mp_image_token_length": 64,
     "vlm_extra_tokens": {
         "image_token": "<|image|>"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d0df67f25cc65078214d3e7e241c3c71fadc637bd409be9fae02992bbe37eb
-size 1840254904
+oid sha256:a270f1eb5d3c832f762ae2f92225a56e4d68ffcff8e5b4f3ffc3efce01af9ac5
+size 1802506128