Upload nanoVLM using push_to_hub

config.json

@@ -15,8 +15,8 @@
     "lm_re_base": 100000,
     "lm_max_position_embeddings": 8192,
     "lm_base_vocab_size": 49152,
-    "extra_token_amount": 1,
-    "lm_vocab_size": 49153,
+    "extra_token_amount": 17,
+    "lm_vocab_size": 49169,
     "lm_n_heads": 15,
     "lm_n_kv_heads": 5,
     "lm_dropout": 0.0,
@@ -30,8 +30,25 @@
     "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 %}",
     "mp_pixel_shuffle_factor": 4,
     "mp_image_token_length": 64,
+    "max_img_size": 512,
     "vlm_extra_tokens": {
-        "image_token": "<|image|>"
+        "image_token": "<|image|>",
+        "r1c1": "<row_1_col_1>",
+        "r1c2": "<row_1_col_2>",
+        "r1c3": "<row_1_col_3>",
+        "r1c4": "<row_1_col_4>",
+        "r2c1": "<row_2_col_1>",
+        "r2c2": "<row_2_col_2>",
+        "r2c3": "<row_2_col_3>",
+        "r2c4": "<row_2_col_4>",
+        "r3c1": "<row_3_col_1>",
+        "r3c2": "<row_3_col_2>",
+        "r3c3": "<row_3_col_3>",
+        "r3c4": "<row_3_col_4>",
+        "r4c1": "<row_4_col_1>",
+        "r4c2": "<row_4_col_2>",
+        "r4c3": "<row_4_col_3>",
+        "r4c4": "<row_4_col_4>"
     },
     "vlm_load_backbone_weights": true,
     "vlm_checkpoint_path": "checkpoints",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181966c24cde0c20903be111156cf3f68b316f2f33dde3f5e030f71fd3b95d94
-size 1840254904
+oid sha256:dcb7199d21d41d1ada921a9932d7af7c6ee65772750992a26f3ddd47556bcf9a
+size 1840316344