Upload nanoVLM using push_to_hub

config.json

@@ -9,29 +9,29 @@
     "vit_ln_eps": 1e-06,
     "vit_cls_flag": false,
     "vit_model_type": "google/siglip2-base-patch16-512",
-    "lm_hidden_dim": 576,
-    "lm_inter_dim": 1536,
+    "lm_hidden_dim": 960,
+    "lm_inter_dim": 2560,
     "lm_rms_eps": 1e-05,
     "lm_re_base": 100000,
     "lm_max_position_embeddings": 8192,
     "lm_base_vocab_size": 49152,
     "extra_token_amount": 66,
     "lm_vocab_size": 49218,
-    "lm_n_heads": 9,
-    "lm_n_kv_heads": 3,
+    "lm_n_heads": 15,
+    "lm_n_kv_heads": 5,
     "lm_dropout": 0.0,
-    "lm_n_blocks": 30,
+    "lm_n_blocks": 32,
     "lm_attn_scaling": 1.0,
-    "lm_max_length": 256,
+    "lm_max_length": 4096,
     "lm_use_tokens": false,
     "lm_tie_weights": true,
-    "lm_model_type": "HuggingFaceTB/SmolLM2-135M",
+    "lm_model_type": "HuggingFaceTB/SmolLM2-360M-Instruct",
     "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 %}",
     "mp_pixel_shuffle_factor": 4,
     "mp_image_token_length": 64,
-    "max_img_size": 512,
-    "resize_to_max_side_len": false,
+    "max_img_size": 2048,
+    "resize_to_max_side_len": true,
     "vlm_extra_tokens": {
         "image_token": "<|image|>",
         "global_image_token": "<|global_image|>",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f71bb4db4cb339669078ad8820ab3f1fe580ebeacd637f493102baacc5f18b6
-size 912301840
+oid sha256:a3191fce850b9854588ebf562719fb19517bbd2b818d9d0d81f178cda6559db3
+size 1840504504