Upload nanoVLM using push_to_hub

config.json

@@ -15,14 +15,14 @@
     "lm_re_base": 100000,
     "lm_max_position_embeddings": 8192,
     "lm_base_vocab_size": 49152,
-    "extra_token_amount": 17,
-    "lm_vocab_size": 49169,
+    "extra_token_amount": 65,
+    "lm_vocab_size": 49217,
     "lm_n_heads": 15,
     "lm_n_kv_heads": 5,
     "lm_dropout": 0.0,
     "lm_n_blocks": 32,
     "lm_attn_scaling": 1.0,
-    "lm_max_length": 1024,
+    "lm_max_length": 4096,
     "lm_use_tokens": false,
     "lm_tie_weights": true,
     "lm_model_type": "HuggingFaceTB/SmolLM2-360M-Instruct",
@@ -30,25 +30,73 @@
     "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": 1024,
+    "max_img_size": 2048,
     "vlm_extra_tokens": {
         "image_token": "<|image|>",
         "r1c1": "<row_1_col_1>",
         "r1c2": "<row_1_col_2>",
         "r1c3": "<row_1_col_3>",
         "r1c4": "<row_1_col_4>",
+        "r1c5": "<row_1_col_5>",
+        "r1c6": "<row_1_col_6>",
+        "r1c7": "<row_1_col_7>",
+        "r1c8": "<row_1_col_8>",
         "r2c1": "<row_2_col_1>",
         "r2c2": "<row_2_col_2>",
         "r2c3": "<row_2_col_3>",
         "r2c4": "<row_2_col_4>",
+        "r2c5": "<row_2_col_5>",
+        "r2c6": "<row_2_col_6>",
+        "r2c7": "<row_2_col_7>",
+        "r2c8": "<row_2_col_8>",
         "r3c1": "<row_3_col_1>",
         "r3c2": "<row_3_col_2>",
         "r3c3": "<row_3_col_3>",
         "r3c4": "<row_3_col_4>",
+        "r3c5": "<row_3_col_5>",
+        "r3c6": "<row_3_col_6>",
+        "r3c7": "<row_3_col_7>",
+        "r3c8": "<row_3_col_8>",
         "r4c1": "<row_4_col_1>",
         "r4c2": "<row_4_col_2>",
         "r4c3": "<row_4_col_3>",
-        "r4c4": "<row_4_col_4>"
+        "r4c4": "<row_4_col_4>",
+        "r4c5": "<row_4_col_5>",
+        "r4c6": "<row_4_col_6>",
+        "r4c7": "<row_4_col_7>",
+        "r4c8": "<row_4_col_8>",
+        "r5c1": "<row_5_col_1>",
+        "r5c2": "<row_5_col_2>",
+        "r5c3": "<row_5_col_3>",
+        "r5c4": "<row_5_col_4>",
+        "r5c5": "<row_5_col_5>",
+        "r5c6": "<row_5_col_6>",
+        "r5c7": "<row_5_col_7>",
+        "r5c8": "<row_5_col_8>",
+        "r6c1": "<row_6_col_1>",
+        "r6c2": "<row_6_col_2>",
+        "r6c3": "<row_6_col_3>",
+        "r6c4": "<row_6_col_4>",
+        "r6c5": "<row_6_col_5>",
+        "r6c6": "<row_6_col_6>",
+        "r6c7": "<row_6_col_7>",
+        "r6c8": "<row_6_col_8>",
+        "r7c1": "<row_7_col_1>",
+        "r7c2": "<row_7_col_2>",
+        "r7c3": "<row_7_col_3>",
+        "r7c4": "<row_7_col_4>",
+        "r7c5": "<row_7_col_5>",
+        "r7c6": "<row_7_col_6>",
+        "r7c7": "<row_7_col_7>",
+        "r7c8": "<row_7_col_8>",
+        "r8c1": "<row_8_col_1>",
+        "r8c2": "<row_8_col_2>",
+        "r8c3": "<row_8_col_3>",
+        "r8c4": "<row_8_col_4>",
+        "r8c5": "<row_8_col_5>",
+        "r8c6": "<row_8_col_6>",
+        "r8c7": "<row_8_col_7>",
+        "r8c8": "<row_8_col_8>"
     },
     "vlm_load_backbone_weights": true,
     "vlm_checkpoint_path": "checkpoints",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3365b16004533507d6de88fec0bc8f2cd739960bb11e9d07bc4bcb90e986e0f7
-size 1840316344
+oid sha256:dae42036d7a15464f763a342c2df3b7727998de9555a7f1d579609450b68cd8c
+size 1840500664