Push model using huggingface_hub.

README.md

@@ -0,0 +1,13 @@
+---
+library_name: nanovlm
+license: mit
+tags:
+- image-text-to-text
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/huggingface/nanoVLM
+- Paper: [More Information Needed]
+- Docs: [More Information Needed]

config.json

@@ -0,0 +1,34 @@
+{
+  "cfg": {
+    "lm_attn_scaling": 1.0,
+    "lm_dropout": 0.0,
+    "lm_eos_token_id": 0,
+    "lm_hidden_dim": 576,
+    "lm_inter_dim": 1536,
+    "lm_max_length": 79,
+    "lm_max_position_embeddings": 8192,
+    "lm_model_type": "HuggingFaceTB/SmolLM2-135M",
+    "lm_n_blocks": 30,
+    "lm_n_heads": 9,
+    "lm_n_kv_heads": 3,
+    "lm_re_base": 100000,
+    "lm_rms_eps": 1e-05,
+    "lm_tie_weights": true,
+    "lm_tokenizer": "HuggingFaceTB/cosmo2-tokenizer",
+    "lm_use_tokens": false,
+    "lm_vocab_size": 49152,
+    "mp_pixel_shuffle_factor": 2,
+    "vit_cls_flag": false,
+    "vit_dropout": 0.0,
+    "vit_hidden_dim": 768,
+    "vit_img_size": 224,
+    "vit_inter_dim": 3072,
+    "vit_ln_eps": 1e-06,
+    "vit_model_type": "google/siglip-base-patch16-224",
+    "vit_n_blocks": 12,
+    "vit_n_heads": 12,
+    "vit_patch_size": 16,
+    "vlm_checkpoint_path": "nanoVLM.pth",
+    "vlm_load_backbone_weights": true
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99828a24ee9868f81c746cc38b773bcbe95d8d71ca65595db4f4b0ca0e90c5d3
+size 888372464