Add files using upload-large-folder tool

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/data/chris/hf/7b",
+  "architectures": [
+    "MOLMoForCausalLM"
+  ],
+  "clip_qkv": null,
+  "embedding_size": 152064,
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 37888,
+  "layer_norm_eps": 1e-06,
+  "max_position_embeddings": 4096,
+  "model_type": "molmo",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "qkv_bias": true,
+  "rope_theta": 1000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "use_position_ids": true,
+  "vocab_size": 152064,
+  "weight_tying": false
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.43.3"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3877e2be156fa08e67adc932cf812e7be6a41f1cb2e6be17044ab778a6a10965
+size 4978535144

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c402c3dacb85a010c22f3472090e5b1cbefe8386a7cc79755c8820503a9635
+size 4984150504

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed917e44b920a8b56a7db53e8a0641a447dd8630e36d76abef857a6883306b9a
+size 4727238936

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604f0181f708d1d6c56e8cd06aea74e43922985afbcd83d62e3fed3565837804
+size 4661160008

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a5046ae726c9e5cdeb27f891486c35c921f95fd582ee6a5b897b9e554a80c9
+size 4661160008

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b034831173c907ec577af6a8297a4fdb5385ecd861b13c0c12f3d0072b080c4
+size 4272090496

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225404ed62c82967fdbaf7a17a8024d0b1af37c55f7469b2196b5c7943c93955
+size 3799830480

model.safetensors.index.json

@@ -0,0 +1,591 @@
+{
+  "metadata": {
+    "total_size": 32084084736
+  },
+  "weight_map": {
+    "model.transformer.blocks.0.att_proj.bias": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.0.att_proj.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.0.attn_norm.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.0.attn_out.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.0.ff_norm.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.0.ff_out.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.0.ff_proj.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.1.att_proj.bias": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.1.att_proj.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.1.attn_norm.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.1.attn_out.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.1.ff_norm.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.1.ff_out.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.1.ff_proj.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.10.att_proj.bias": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.10.att_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.10.attn_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.10.attn_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.10.ff_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.10.ff_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.10.ff_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.11.att_proj.bias": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.11.att_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.11.attn_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.11.attn_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.11.ff_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.11.ff_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.11.ff_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.12.att_proj.bias": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.12.att_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.12.attn_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.12.attn_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.12.ff_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.12.ff_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.12.ff_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.13.att_proj.bias": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.13.att_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.13.attn_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.13.attn_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.13.ff_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.13.ff_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.13.ff_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.14.att_proj.bias": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.14.att_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.14.attn_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.14.attn_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.14.ff_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.14.ff_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.14.ff_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.15.att_proj.bias": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.15.att_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.15.attn_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.15.attn_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.15.ff_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.15.ff_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.15.ff_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.16.att_proj.bias": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.16.att_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.16.attn_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.16.attn_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.16.ff_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.16.ff_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.16.ff_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.17.att_proj.bias": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.17.att_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.17.attn_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.17.attn_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.17.ff_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.17.ff_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.17.ff_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.18.att_proj.bias": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.18.att_proj.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.18.attn_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.18.attn_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.18.ff_norm.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.18.ff_out.weight": "model-00004-of-00007.safetensors",
+    "model.transformer.blocks.18.ff_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.19.att_proj.bias": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.19.att_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.19.attn_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.19.attn_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.19.ff_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.19.ff_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.19.ff_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.2.att_proj.bias": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.2.att_proj.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.2.attn_norm.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.2.attn_out.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.2.ff_norm.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.2.ff_out.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.2.ff_proj.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.blocks.20.att_proj.bias": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.20.att_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.20.attn_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.20.attn_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.20.ff_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.20.ff_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.20.ff_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.21.att_proj.bias": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.21.att_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.21.attn_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.21.attn_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.21.ff_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.21.ff_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.21.ff_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.22.att_proj.bias": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.22.att_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.22.attn_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.22.attn_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.22.ff_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.22.ff_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.22.ff_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.23.att_proj.bias": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.23.att_proj.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.23.attn_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.23.attn_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.23.ff_norm.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.23.ff_out.weight": "model-00005-of-00007.safetensors",
+    "model.transformer.blocks.23.ff_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.24.att_proj.bias": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.24.att_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.24.attn_norm.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.24.attn_out.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.24.ff_norm.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.24.ff_out.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.24.ff_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.25.att_proj.bias": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.25.att_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.25.attn_norm.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.25.attn_out.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.25.ff_norm.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.25.ff_out.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.25.ff_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.26.att_proj.bias": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.26.att_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.26.attn_norm.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.26.attn_out.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.26.ff_norm.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.26.ff_out.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.26.ff_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.27.att_proj.bias": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.27.att_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.27.attn_norm.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.27.attn_out.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.27.ff_norm.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.27.ff_out.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.27.ff_proj.weight": "model-00006-of-00007.safetensors",
+    "model.transformer.blocks.3.att_proj.bias": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.3.att_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.3.attn_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.3.attn_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.3.ff_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.3.ff_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.3.ff_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.4.att_proj.bias": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.4.att_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.4.attn_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.4.attn_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.4.ff_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.4.ff_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.4.ff_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.5.att_proj.bias": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.5.att_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.5.attn_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.5.attn_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.5.ff_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.5.ff_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.5.ff_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.6.att_proj.bias": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.6.att_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.6.attn_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.6.attn_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.6.ff_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.6.ff_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.6.ff_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.7.att_proj.bias": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.7.att_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.7.attn_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.7.attn_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.7.ff_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.7.ff_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.7.ff_proj.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.8.att_proj.bias": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.8.att_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.8.attn_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.8.attn_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.8.ff_norm.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.8.ff_out.weight": "model-00002-of-00007.safetensors",
+    "model.transformer.blocks.8.ff_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.9.att_proj.bias": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.9.att_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.9.attn_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.9.attn_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.9.ff_norm.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.9.ff_out.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.blocks.9.ff_proj.weight": "model-00003-of-00007.safetensors",
+    "model.transformer.ff_out.weight": "model-00007-of-00007.safetensors",
+    "model.transformer.ln_f.weight": "model-00001-of-00007.safetensors",
+    "model.transformer.wte.embedding": "model-00001-of-00007.safetensors",
+    "model.transformer.wte.new_embedding": "model-00001-of-00007.safetensors",
+    "model.vision_backbone.image_pooling_2d.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_pooling_2d.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_pooling_2d.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_pooling_2d.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_pooling_2d.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_pooling_2d.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_pooling_2d.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_pooling_2d.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_projector.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_projector.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_projector.w3.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.class_embedding": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.patch_embedding.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.positional_embedding": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.pre_ln.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.pre_ln.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.0.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.1.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.10.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.11.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.12.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.13.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.14.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.15.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.16.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.17.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.18.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.19.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.2.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.20.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.21.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.22.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.3.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.4.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.5.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.6.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.7.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.8.ffn_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention.wk.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention.wk.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention.wo.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention.wo.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention.wq.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention.wq.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention.wv.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention.wv.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.attention_norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.feed_forward.w1.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.feed_forward.w1.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.feed_forward.w2.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.feed_forward.w2.weight": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.ffn_norm.bias": "model-00007-of-00007.safetensors",
+    "model.vision_backbone.image_vit.transformer.resblocks.9.ffn_norm.weight": "model-00007-of-00007.safetensors"
+  }
+}