Upload nanoVLM using push_to_hub

config.json

@@ -22,15 +22,15 @@
     "lm_dropout": 0.0,
     "lm_n_blocks": 32,
     "lm_attn_scaling": 1.0,
-    "lm_max_length": 1024,
+    "lm_max_length": 2048,
     "lm_use_tokens": false,
     "lm_tie_weights": true,
     "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 %}",
     "lm_eos_token_id": 0,
-    "mp_pixel_shuffle_factor": 2,
-    "mp_image_token_length": 256,
+    "mp_pixel_shuffle_factor": 4,
+    "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:dd335d4fe5f770fdaefac798dd7a2a2ef1f3d8c4a0a5d68f2f46781890d6d7b3
-size 1804865424
+oid sha256:9261e777d4075adb266e93a1ebd44868756d2ad7050c8ede48441bd269d0ebb2
+size 1840254904