Upload nanoVLM using push_to_hub

README.md

@@ -1,27 +1,27 @@
-
----
-# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
-# Doc / guide: https://huggingface.co/docs/hub/model-cards
-library_name: nanovlm
-license: mit
-pipeline_tag: image-text-to-text
-tags:
-  - vision-language
-  - multimodal
-  - research
----
-
-**nanoVLM** is a minimal and lightweight Vision-Language Model (VLM) designed for efficient training and experimentation. Built using pure PyTorch, the entire model architecture and training logic fits within ~750 lines of code. It combines a ViT-based image encoder (SigLIP-B/16-224-85M) with a lightweight causal language model (SmolLM2-135M), resulting in a compact 222M parameter model.
-
-For more information, check out the base model on https://huggingface.co/lusxvr/nanoVLM-222M.
-
-**Usage:**
-
-Clone the nanoVLM repository: https://github.com/huggingface/nanoVLM.
-Follow the install instructions and run the following code:
-
-```python
-from models.vision_language_model import VisionLanguageModel
-
-model = VisionLanguageModel.from_pretrained("jaehyeono/nanoVLM")
-```
+
+---
+# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
+# Doc / guide: https://huggingface.co/docs/hub/model-cards
+library_name: nanovlm
+license: mit
+pipeline_tag: image-text-to-text
+tags:
+  - vision-language
+  - multimodal
+  - research
+---
+
+**nanoVLM** is a minimal and lightweight Vision-Language Model (VLM) designed for efficient training and experimentation. Built using pure PyTorch, the entire model architecture and training logic fits within ~750 lines of code. It combines a ViT-based image encoder (SigLIP-B/16-224-85M) with a lightweight causal language model (SmolLM2-135M), resulting in a compact 222M parameter model.
+
+For more information, check out the base model on https://huggingface.co/lusxvr/nanoVLM-222M.
+
+**Usage:**
+
+Clone the nanoVLM repository: https://github.com/huggingface/nanoVLM.
+Follow the install instructions and run the following code:
+
+```python
+from models.vision_language_model import VisionLanguageModel
+
+model = VisionLanguageModel.from_pretrained("jaehyeono/nanoVLM")
+```

config.json

@@ -1,40 +1,39 @@
-{
-    "vit_hidden_dim": 768,
-    "vit_inter_dim": 3072,
-    "vit_patch_size": 16,
-    "vit_img_size": 224,
-    "vit_n_heads": 12,
-    "vit_dropout": 0.0,
-    "vit_n_blocks": 12,
-    "vit_ln_eps": 1e-06,
-    "vit_cls_flag": false,
-    "vit_model_type": "google/siglip-base-patch16-224",
-    "lm_hidden_dim": 576,
-    "lm_inter_dim": 1536,
-    "lm_rms_eps": 1e-05,
-    "lm_re_base": 100000,
-    "lm_max_position_embeddings": 8192,
-    "lm_base_vocab_size": 49152,
-    "extra_token_amount": 1,
-    "lm_vocab_size": 49153,
-    "lm_n_heads": 9,
-    "lm_n_kv_heads": 3,
-    "lm_dropout": 0.0,
-    "lm_n_blocks": 30,
-    "lm_attn_scaling": 1.0,
-    "lm_eos_token_id": 0,
-    "lm_max_length": 128,
-    "lm_use_tokens": false,
-    "lm_tie_weights": true,
-    "lm_model_type": "HuggingFaceTB/SmolLM2-135M",
-    "lm_tokenizer": "HuggingFaceTB/cosmo2-tokenizer",
-    "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": 2,
-    "mp_image_token_length": 49,
-    "vlm_extra_tokens": {
-        "image_token": "<|image|>"
-    },
-    "vlm_load_backbone_weights": true,
-    "vlm_checkpoint_path": "checkpoints",
-    "hf_repo_name": "nanoVLM"
+{
+    "vit_hidden_dim": 768,
+    "vit_inter_dim": 3072,
+    "vit_patch_size": 16,
+    "vit_img_size": 224,
+    "vit_n_heads": 12,
+    "vit_dropout": 0.0,
+    "vit_n_blocks": 12,
+    "vit_ln_eps": 1e-06,
+    "vit_cls_flag": false,
+    "vit_model_type": "google/siglip-base-patch16-224",
+    "lm_hidden_dim": 576,
+    "lm_inter_dim": 1536,
+    "lm_rms_eps": 1e-05,
+    "lm_re_base": 100000,
+    "lm_max_position_embeddings": 8192,
+    "lm_base_vocab_size": 49152,
+    "extra_token_amount": 1,
+    "lm_vocab_size": 49153,
+    "lm_n_heads": 9,
+    "lm_n_kv_heads": 3,
+    "lm_dropout": 0.0,
+    "lm_n_blocks": 30,
+    "lm_attn_scaling": 1.0,
+    "lm_max_length": 128,
+    "lm_use_tokens": false,
+    "lm_tie_weights": true,
+    "lm_model_type": "HuggingFaceTB/SmolLM2-135M",
+    "lm_tokenizer": "HuggingFaceTB/cosmo2-tokenizer",
+    "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": 2,
+    "mp_image_token_length": 49,
+    "vlm_extra_tokens": {
+        "image_token": "<|image|>"
+    },
+    "vlm_load_backbone_weights": true,
+    "vlm_checkpoint_path": "checkpoints",
+    "hf_repo_name": "nanoVLM"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9738e1c261723567a2981eeb028f84507c03693332f6928df3c8e3fc77dcdb0a
+oid sha256:eb46182a5cc4a0e4dd7187fc77554b2a9928efa6b62ef4ac529c2306af209f51
 size 888374768