Upload 11 files

Paligemma 3B Added Tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image>": 257152
+}

Paligemma 3B Index.json

@@ -0,0 +1,610 @@
+{
+  "metadata": {
+    "total_size": 11693865920
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
+    "multi_modal_projector.linear.bias": "model-00001-of-00003.safetensors",
+    "multi_modal_projector.linear.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00003.safetensors"
+  }
+}

Paligemma 3B PT 224 README.md

@@ -0,0 +1,845 @@
+---
+license: gemma
+library_name: transformers
+extra_gated_heading: Access PaliGemma on Hugging Face
+extra_gated_prompt: To access PaliGemma on Hugging Face, you’re required to review
+  and agree to Google’s usage license. To do this, please ensure you’re logged-in
+  to Hugging Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
+pipeline_tag: image-text-to-text
+---
+# PaliGemma model card
+
+**Model page:** [PaliGemma](https://ai.google.dev/gemma/docs/paligemma)
+
+Transformers PaliGemma 3B weights, pre-trained with 224*224 input images and 128 token input/output text sequences. The models are available in float32, bfloat16 and float16 formats for fine-tuning.
+
+**Resources and technical documentation:**
+
+*   [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
+*   [PaliGemma on Kaggle](https://www.kaggle.com/models/google/paligemma)
+*   [PaliGemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/363)
+
+**Terms of Use:** [Terms](https://ai.google.dev/gemma/terms)
+
+**Authors:** Google
+
+## Model information
+
+### Model summary
+
+#### Description
+
+PaliGemma is a versatile and lightweight vision-language model (VLM) inspired by
+[PaLI-3](https://arxiv.org/abs/2310.09199) and based on open components such as
+the [SigLIP vision model](https://arxiv.org/abs/2303.15343) and the [Gemma
+language model](https://arxiv.org/abs/2403.08295). It takes both image and text
+as input and generates text as output, supporting multiple languages. It is designed for class-leading fine-tune performance on a wide range of vision-language tasks such as image and short video caption, visual question answering, text reading, object detection and object segmentation.
+
+#### Model architecture
+
+PaliGemma is the composition of a [Transformer
+decoder](https://arxiv.org/abs/1706.03762) and a [Vision Transformer image
+encoder](https://arxiv.org/abs/2010.11929), with a total of 3 billion
+params. The text decoder is initialized from
+[Gemma-2B](https://www.kaggle.com/models/google/gemma). The image encoder is
+initialized from
+[SigLIP-So400m/14](https://colab.research.google.com/github/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/SigLIP_demo.ipynb).
+PaliGemma is trained following the PaLI-3 recipes.
+
+#### Inputs and outputs
+
+*   **Input:** Image and text string, such as a prompt to caption the image, or
+    a question.
+*   **Output:** Generated text in response to the input, such as a caption of
+    the image, an answer to a question, a list of object bounding box
+    coordinates, or segmentation codewords.
+
+### Model data
+
+#### Pre-train datasets
+
+PaliGemma is pre-trained on the following mixture of datasets:
+
+*   **WebLI:** [WebLI (Web Language Image)](https://arxiv.org/abs/2209.06794) is
+    a web-scale multilingual image-text dataset built from the public web. A
+    wide range of WebLI splits are used to acquire versatile model capabilities,
+    such as visual semantic understanding, object localization,
+    visually-situated text understanding, multilinguality, etc.
+*   **CC3M-35L:** Curated English image-alt_text pairs from webpages ([Sharma et
+    al., 2018](https://aclanthology.org/P18-1238/)). We used the [Google Cloud
+    Translation API](https://cloud.google.com/translate) to translate into 34
+    additional languages.
+*   **VQ²A-CC3M-35L/VQG-CC3M-35L:** A subset of VQ2A-CC3M ([Changpinyo et al.,
+    2022a](https://aclanthology.org/2022.naacl-main.142/)), translated into the
+    same additional 34 languages as CC3M-35L, using the [Google Cloud
+    Translation API](https://cloud.google.com/translate).
+*   **OpenImages:** Detection and object-aware questions and answers
+    ([Piergiovanni et al. 2022](https://arxiv.org/abs/2209.04372)) generated by
+    handcrafted rules on the [OpenImages dataset].
+*   **WIT:** Images and texts collected from Wikipedia ([Srinivasan et al.,
+    2021](https://arxiv.org/abs/2103.01913)).
+
+[OpenImages dataset]: https://storage.googleapis.com/openimages/web/factsfigures_v7.html
+
+#### Data responsibility filtering
+
+The following filters are applied to WebLI, with the goal of training PaliGemma
+on clean data:
+
+*   **Pornographic image filtering:** This filter removes images deemed to be of
+    pornographic nature.
+*   **Text safety filtering:** We identify and filter out images that are paired
+    with unsafe text. Unsafe text is any text deemed to contain or be about
+    CSAI, pornography, vulgarities, or otherwise offensive.
+*   **Text toxicity filtering:** We further use the [Perspective
+    API](https://perspectiveapi.com/) to identify and filter out images that are
+    paired with text deemed insulting, obscene, hateful or otherwise toxic.
+*   **Text personal information filtering:** We filtered certain personal information and other sensitive data using [Cloud Data Loss Prevention (DLP)
+    API](https://cloud.google.com/security/products/dlp) to protect the privacy
+    of individuals. Identifiers such as social security numbers and [other sensitive information types] were removed.
+*   **Additional methods:** Filtering based on content quality and safety in
+    line with our policies and practices.
+
+[other sensitive information types]: https://cloud.google.com/sensitive-data-protection/docs/high-sensitivity-infotypes-reference?_gl=1*jg604m*_ga*ODk5MzA3ODQyLjE3MTAzMzQ3NTk.*_ga_WH2QY8WWF5*MTcxMDUxNTkxMS4yLjEuMTcxMDUxNjA2NC4wLjAuMA..&_ga=2.172110058.-899307842.1710334759
+
+
+
+## How to Use
+
+PaliGemma is a single-turn vision language model not meant for conversational use,
+and it works best when fine-tuning to a specific use case. 
+
+You can configure which task the model will solve by conditioning it with task prefixes,
+such as “detect” or “segment”. The pretrained models were trained in this fashion to imbue
+them with a rich set of capabilities (question answering, captioning, segmentation, etc.).
+However, they are not designed to be used directly, but to be transferred (by fine-tuning)
+to specific tasks using a similar prompt structure. For interactive testing, you can use
+the "mix" family of models, which have been fine-tuned on a mixture of tasks. To see model 
+[google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) in action,
+check [this Space that uses the Transformers codebase](https://huggingface.co/spaces/big-vision/paligemma-hf).
+
+Please, refer to the [usage and limitations section](#usage-and-limitations) for intended
+use cases, or visit the [blog post](https://huggingface.co/blog/paligemma-google-vlm) for
+additional details and examples.
+
+## Use in Transformers
+
+The following snippets use model `google/paligemma-3b-mix-224` for reference purposes.
+The model in this repo you are now browsing may have been trained for other tasks, please
+make sure you use appropriate inputs for the task at hand.
+
+### Running the default precision (`float32`) on CPU
+
+```python
+from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
+from PIL import Image
+import requests
+import torch
+
+model_id = "google/paligemma-3b-mix-224"
+
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
+image = Image.open(requests.get(url, stream=True).raw)
+
+model = PaliGemmaForConditionalGeneration.from_pretrained(model_id).eval()
+processor = AutoProcessor.from_pretrained(model_id)
+
+# Instruct the model to create a caption in Spanish
+prompt = "caption es"
+model_inputs = processor(text=prompt, images=image, return_tensors="pt")
+input_len = model_inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
+    generation = generation[0][input_len:]
+    decoded = processor.decode(generation, skip_special_tokens=True)
+    print(decoded)
+```
+
+Output: `Un auto azul estacionado frente a un edificio.`
+
+### Running other precisions on CUDA
+
+For convenience, the repos contain revisions of the weights already converted to `bfloat16` and `float16`,
+so you can use them to reduce the download size and avoid casting on your local computer.
+
+This is how you'd run `bfloat16` on an nvidia CUDA card.
+
+```python
+from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
+from PIL import Image
+import requests
+import torch
+
+model_id = "google/paligemma-3b-mix-224"
+device = "cuda:0"
+dtype = torch.bfloat16
+
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
+image = Image.open(requests.get(url, stream=True).raw)
+
+model = PaliGemmaForConditionalGeneration.from_pretrained(
+    model_id,
+    torch_dtype=dtype,
+    device_map=device,
+    revision="bfloat16",
+).eval()
+processor = AutoProcessor.from_pretrained(model_id)
+
+# Instruct the model to create a caption in Spanish
+prompt = "caption es"
+model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+input_len = model_inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
+    generation = generation[0][input_len:]
+    decoded = processor.decode(generation, skip_special_tokens=True)
+    print(decoded)
+```
+
+### Loading in 4-bit / 8-bit
+
+You need to install `bitsandbytes` to automatically run inference using 8-bit or 4-bit precision:
+
+```
+pip install bitsandbytes accelerate
+```
+
+```
+from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
+from PIL import Image
+import requests
+import torch
+
+model_id = "google/paligemma-3b-mix-224"
+device = "cuda:0"
+dtype = torch.bfloat16
+
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
+image = Image.open(requests.get(url, stream=True).raw)
+
+quantization_config = BitsAndBytesConfig(load_in_8bit=True)
+
+model = PaliGemmaForConditionalGeneration.from_pretrained(
+    model_id, quantization_config=quantization_config
+).eval()
+processor = AutoProcessor.from_pretrained(model_id)
+
+# Instruct the model to create a caption in Spanish
+prompt = "caption es"
+model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+input_len = model_inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
+    generation = generation[0][input_len:]
+    decoded = processor.decode(generation, skip_special_tokens=True)
+    print(decoded)
+```
+
+## Implementation information
+
+### Hardware
+
+PaliGemma was trained using the latest generation of Tensor Processing Unit
+(TPU) hardware (TPUv5e).
+
+### Software
+
+Training was done using [JAX](https://github.com/google/jax),
+[Flax](https://github.com/google/flax),
+[TFDS](https://github.com/tensorflow/datasets) and
+[`big_vision`](https://github.com/google-research/big_vision).
+
+JAX allows researchers to take advantage of the latest generation of hardware,
+including TPUs, for faster and more efficient training of large models.
+
+TFDS is used to access datasets and Flax is used for model architecture. The
+PaliGemma fine-tune code and inference code are released in the `big_vision`
+GitHub repository.
+
+## Evaluation information
+
+### Benchmark results
+
+In order to verify the transferability of PaliGemma to a wide variety of
+academic tasks, we fine-tune the pretrained models on each task. Additionally we
+train the mix model with a mixture of the transfer tasks. We report results on
+different resolutions to provide an impression of which tasks benefit from
+increased resolution. Importantly, none of these tasks or datasets are part of
+the pretraining data mixture, and their images are explicitly removed from the
+web-scale pre-training data.
+
+#### Single task (fine-tune on single task)
+
+<table>
+  <tbody><tr>
+    <th>Benchmark<br>(train split)</th>
+    <th>Metric<br>(split)</th>
+    <th>pt-224</th>
+    <th>pt-448</th>
+    <th>pt-896</th>
+  </tr>
+  <tr>
+    <th>Captioning</th>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://cocodataset.org/#home">COCO captions</a><br>(train+restval)
+    </td>
+    <td>CIDEr (val)</td>
+    <td>141.92</td>
+    <td>144.60</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://nocaps.org/">NoCaps</a><br>(Eval of COCO<br>captions transfer)
+    </td>
+    <td>CIDEr (val)</td>
+    <td>121.72</td>
+    <td>123.58</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/pdf/2205.12522">COCO-35L</a><br>(train)
+    </td>
+    <td>CIDEr dev<br>(en/avg-34/avg)</td>
+    <td>
+      139.2<br>
+      115.8<br>
+      116.4
+    </td>
+    <td>
+      141.2<br>
+      118.0<br>
+      118.6
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/pdf/2205.12522">XM3600</a><br>(Eval of COCO-35L transfer)
+    </td>
+    <td>CIDEr dev<br>(en/avg-34/avg)</td>
+    <td>
+      78.1<br>
+      41.3<br>
+      42.4
+    </td>
+    <td>
+      80.0<br>
+      41.9<br>
+      42.9
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://textvqa.org/textcaps/">TextCaps</a><br>(train)
+    </td>
+    <td>CIDEr (val)</td>
+    <td>127.48</td>
+    <td>153.94</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2110.11624">SciCap</a><br>(first sentence, no subfigure)<br>(train+val)
+    </td>
+    <td>CIDEr/BLEU-4<br>(test)</td>
+    <td>
+      162.25<br>
+      0.192<br>
+    </td>
+    <td>
+      181.49<br>
+      0.211<br>
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2108.03353">Screen2words</a><br>(train+dev)
+    </td>
+    <td>CIDEr (test)</td>
+    <td>117.57</td>
+    <td>119.59</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2010.04295">Widget Captioning</a><br>(train+dev)
+    </td>
+    <td>CIDEr (test)</td>
+    <td>136.07</td>
+    <td>148.36</td>
+  </tr>
+  <tr>
+    <th>Question answering</th>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://visualqa.org/index.html">VQAv2</a><br>(train+validation)
+    </td>
+    <td>Accuracy<br>(Test server - std)</td>
+    <td>83.19</td>
+    <td>85.64</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2401.06209">MMVP</a><br>(Eval of VQAv2 transfer)
+    </td>
+    <td>Paired Accuracy</td>
+    <td>47.33</td>
+    <td>45.33</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2305.10355">POPE</a><br>(Eval of VQAv2 transfer)
+    </td>
+    <td>Accuracy<br>(random/popular/<br>adversarial)</td>
+    <td>
+      87.80<br>
+      85.87<br>
+      84.27
+    </td>
+    <td>
+      88.23<br>
+      86.77<br>
+      85.90
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://okvqa.allenai.org/">OKVQA</a><br>(train)
+    </td>
+    <td>Accuracy (val)</td>
+    <td>63.54</td>
+    <td>63.15</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (MC)<br>(train+val)
+    </td>
+    <td>Accuracy<br>(Test server)</td>
+    <td>76.37</td>
+    <td>76.90</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (DA)<br>(train+val)
+    </td>
+    <td>Accuracy<br>(Test server)</td>
+    <td>61.85</td>
+    <td>63.22</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a><br>(train_balanced+<br>val_balanced)
+    </td>
+    <td>Accuracy<br>(testdev balanced)</td>
+    <td>65.61</td>
+    <td>67.03</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://aclanthology.org/2022.findings-acl.196/">xGQA</a><br>(Eval of GQA transfer)
+    </td>
+    <td>Mean Accuracy<br>(bn, de, en, id,<br>ko, pt, ru, zh)</td>
+    <td>58.37</td>
+    <td>59.07</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://lil.nlp.cornell.edu/nlvr/">NLVR2</a><br>(train+dev)
+    </td>
+    <td>Accuracy (test)</td>
+    <td>90.02</td>
+    <td>88.93</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://marvl-challenge.github.io/">MaRVL</a><br>(Eval of NLVR2 transfer)
+    </td>
+    <td>Mean Accuracy<br>(test)<br>(id, sw, ta, tr, zh)</td>
+    <td>80.57</td>
+    <td>76.78</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://allenai.org/data/diagrams">AI2D</a><br>(train)
+    </td>
+    <td>Accuracy (test)</td>
+    <td>72.12</td>
+    <td>73.28</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://scienceqa.github.io/">ScienceQA</a><br>(Img subset, no CoT)<br>(train+val)
+    </td>
+    <td>Accuracy (test)</td>
+    <td>95.39</td>
+    <td>95.93</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://zenodo.org/records/6344334">RSVQA-LR</a> (Non numeric)<br>(train+val)
+    </td>
+    <td>Mean Accuracy<br>(test)</td>
+    <td>92.65</td>
+    <td>93.11</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://zenodo.org/records/6344367">RSVQA-HR</a> (Non numeric)<br>(train+val)
+    </td>
+    <td>Mean Accuracy<br>(test/test2)</td>
+    <td>
+      92.61<br>
+      90.58
+    </td>
+    <td>
+      92.79<br>
+      90.54
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2203.10244">ChartQA</a><br>(human+aug)x(train+val)
+    </td>
+    <td>Mean Relaxed<br>Accuracy<br>(test_human,<br>test_aug)</td>
+    <td>57.08</td>
+    <td>71.36</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://vizwiz.org/tasks-and-datasets/vqa/">VizWiz VQA</a><br>(train+val)
+    </td>
+    <td>Accuracy<br>(Test server - std)</td>
+    <td>
+      73.7
+    </td>
+    <td>
+      75.52
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/1810.12440">TallyQA</a><br>(train)
+    </td>
+    <td>Accuracy<br>(test_simple/<br>test_complex)</td>
+    <td>
+      81.72<br>
+      69.56
+    </td>
+    <td>
+      84.86<br>
+      72.27
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://ocr-vqa.github.io/">OCR-VQA</a><br>(train+val)
+    </td>
+    <td>Accuracy (test)</td>
+    <td>72.32</td>
+    <td>74.61</td>
+    <td>74.93</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://textvqa.org/">TextVQA</a><br>(train+val)
+    </td>
+    <td>Accuracy<br>(Test server - std)</td>
+    <td>55.47</td>
+    <td>73.15</td>
+    <td>76.48</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://www.docvqa.org/">DocVQA</a><br>(train+val)
+    </td>
+    <td>ANLS (Test server)</td>
+    <td>43.74</td>
+    <td>78.02</td>
+    <td>84.77</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://openaccess.thecvf.com/content/WACV2022/papers/Mathew_InfographicVQA_WACV_2022_paper.pdf">Infographic VQA</a><br>(train+val)
+    </td>
+    <td>ANLS (Test server)</td>
+    <td>28.46</td>
+    <td>40.47</td>
+    <td>47.75</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/1905.13648">SceneText VQA</a><br>(train+val)
+    </td>
+    <td>ANLS (Test server)</td>
+    <td>63.29</td>
+    <td>81.82</td>
+    <td>84.40</td>
+  </tr>
+  <tr>
+    <th>Segmentation</th>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/1608.00272">RefCOCO</a><br>(combined refcoco, refcoco+,<br>refcocog excluding val<br>and test images)
+    </td>
+    <td>MIoU<br>(validation)<br>refcoco/refcoco+/<br>refcocog</td>
+    <td>
+      73.40<br>
+      68.32<br>
+      67.65
+    </td>
+    <td>
+      75.57<br>
+      69.76<br>
+      70.17
+    </td>
+    <td>
+      76.94<br>
+      72.18<br>
+      72.22
+    </td>
+  </tr>
+  <tr>
+    <th>Video tasks (Caption/QA)</th>
+  </tr>
+  <tr>
+    <td>MSR-VTT (Captioning)</td>
+    <td>CIDEr (test)</td>
+    <td>70.54</td>
+  </tr>
+  <tr>
+    <td>MSR-VTT (QA)</td>
+    <td>Accuracy (test)</td>
+    <td>50.09</td>
+  </tr>
+  <tr>
+    <td>ActivityNet (Captioning)</td>
+    <td>CIDEr (test)</td>
+    <td>34.62</td>
+  </tr>
+  <tr>
+    <td>ActivityNet (QA)</td>
+    <td>Accuracy (test)</td>
+    <td>50.78</td>
+  </tr>
+  <tr>
+    <td>VATEX (Captioning)</td>
+    <td>CIDEr (test)</td>
+    <td>79.73</td>
+  </tr>
+  <tr>
+    <td>MSVD (QA)</td>
+    <td>Accuracy (test)</td>
+    <td>60.22</td>
+  </tr>
+</tbody></table>
+
+#### Mix model (fine-tune on mixture of transfer tasks)
+
+<table>
+  <tbody><tr>
+    <th>Benchmark</th>
+    <th>Metric (split)</th>
+    <th>mix-224</th>
+    <th>mix-448</th>
+  </tr>
+  <tr>
+    <td><a href="https://arxiv.org/abs/2401.06209">MMVP</a></td>
+    <td>Paired Accuracy</td>
+    <td>46.00</td>
+    <td>45.33</td>
+  </tr>
+  <tr>
+    <td><a href="https://arxiv.org/abs/2305.10355">POPE</a></td>
+    <td>Accuracy<br>(random/popular/adversarial)</td>
+    <td>
+      88.00<br>
+      86.63<br>
+      85.67
+    </td>
+    <td>
+      89.37<br>
+      88.40<br>
+      87.47
+    </td>
+  </tr>
+</tbody></table>
+
+## Ethics and safety
+
+### Evaluation approach
+
+Our evaluation methods include structured evaluations and internal red-teaming
+testing of relevant content policies. Red-teaming was conducted by a number of
+different teams, each with different goals and human evaluation metrics. These
+models were evaluated against a number of different categories relevant to
+ethics and safety, including:
+
+*   Human evaluation on prompts covering child safety, content safety and
+    representational harms. See the [Gemma model
+    card](https://ai.google.dev/gemma/docs/model_card#evaluation_approach) for
+    more details on evaluation approach, but with image captioning and visual
+    question answering setups.
+*   Image-to-Text benchmark evaluation: Benchmark against relevant academic
+    datasets such as FairFace Dataset ([Karkkainen et al.,
+    2021](https://arxiv.org/abs/1908.04913)).
+
+### Evaluation results
+
+*   The human evaluation results of ethics and safety evaluations are within
+    acceptable thresholds for meeting [internal
+    policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11)
+    for categories such as child safety, content safety and representational
+    harms.
+*   On top of robust internal evaluations, we also use the Perspective API
+    (threshold of 0.8) to measure toxicity, profanity, and other potential
+    issues in the generated captions for images sourced from the FairFace
+    dataset. We report the maximum and median values observed across subgroups
+    for each of the perceived gender, ethnicity, and age attributes.
+
+
+<table>
+  <tbody><tr>
+    </tr></tbody><tbody><tr><th>Metric</th>
+    <th>Perceived<br>gender</th>
+    <th></th>
+    <th>Ethnicity</th>
+    <th></th>
+    <th>Age group</th>
+    <th></th>
+  </tr>
+  <tr>
+    <th></th>
+    <th>Maximum</th>
+    <th>Median</th>
+    <th>Maximum</th>
+    <th>Median</th>
+    <th>Maximum</th>
+    <th>Median</th>
+  </tr>
+  <tr>
+    <td>Toxicity</td>
+    <td>0.04%</td>
+    <td>0.03%</td>
+    <td>0.08%</td>
+    <td>0.00%</td>
+    <td>0.09%</td>
+    <td>0.00%</td>
+  </tr>
+  <tr>
+    <td>Identity Attack</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+  </tr>
+  <tr>
+    <td>Insult</td>
+    <td>0.06%</td>
+    <td>0.04%</td>
+    <td>0.09%</td>
+    <td>0.07%</td>
+    <td>0.16%</td>
+    <td>0.00%</td>
+  </tr>
+  <tr>
+    <td>Threat</td>
+    <td>0.06%</td>
+    <td>0.05%</td>
+    <td>0.14%</td>
+    <td>0.05%</td>
+    <td>0.17%</td>
+    <td>0.00%</td>
+  </tr>
+  <tr>
+    <td>Profanity</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+  </tr>
+</tbody></table>
+
+## Usage and limitations
+
+### Intended usage
+
+Open Vision Language Models (VLMs) have a wide range of applications across
+various industries and domains. The following list of potential uses is not
+comprehensive. The purpose of this list is to provide contextual information
+about the possible use-cases that the model creators considered as part of model
+training and development.
+
+Fine-tune on specific vision-language task:
+
+*   The pre-trained models can be fine-tuned on a wide range of vision-language
+    tasks such as: image captioning, short video caption, visual question
+    answering, text reading, object detection and object segmentation.
+*   The pre-trained models can be fine-tuned for specific domains such as remote
+    sensing question answering, visual questions from people who are blind,
+    science question answering, describe UI element functionalities.
+*   The pre-trained models can be fine-tuned for tasks with non-textual outputs
+    such as bounding boxes or segmentation masks.
+
+Vision-language research:
+
+*   The pre-trained models and fine-tuned models can serve as a foundation for researchers to experiment with VLM
+    techniques, develop algorithms, and contribute to the advancement of the
+    field.
+
+### Ethical considerations and risks
+
+The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following:
+
+*   Bias and Fairness
+    *   VLMs trained on large-scale, real-world image-text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card.
+*   Misinformation and Misuse
+    *   VLMs can be misused to generate text that is false, misleading, or harmful.
+    *   Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](https://ai.google.dev/responsible).
+*   Transparency and Accountability
+    *   This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
+    *   A responsibly developed open model offers the opportunity to share innovation by making VLM technology accessible to developers and researchers across the AI ecosystem.
+
+
+Risks identified and mitigations:
+
+*   **Perpetuation of biases:** It's encouraged to perform continuous monitoring
+    (using evaluation metrics, human review) and the exploration of de-biasing
+    techniques during model training, fine-tuning, and other use cases.
+*   **Generation of harmful content:** Mechanisms and guidelines for content
+    safety are essential. Developers are encouraged to exercise caution and
+    implement appropriate content safety safeguards based on their specific
+    product policies and application use cases.
+*   **Misuse for malicious purposes:** Technical limitations and developer and
+    end-user education can help mitigate against malicious applications of LLMs.
+    Educational resources and reporting mechanisms for users to flag misuse are
+    provided. Prohibited uses of Gemma models are outlined in the [Gemma
+    Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
+*   **Privacy violations:** Models were trained on data filtered to remove certain personal information and sensitive data. Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques.
+
+### Limitations
+
+*   Most limitations inherited from the underlying Gemma model still apply:
+    *   VLMs are better at tasks that can be framed with clear prompts and
+        instructions. Open-ended or highly complex tasks might be challenging.
+    *   Natural language is inherently complex. VLMs might struggle to grasp
+        subtle nuances, sarcasm, or figurative language.
+    *   VLMs generate responses based on information they learned from their
+        training datasets, but they are not knowledge bases. They may generate
+        incorrect or outdated factual statements.
+    *   VLMs rely on statistical patterns in language and images. They might
+        lack the ability to apply common sense reasoning in certain situations.
+*   PaliGemma was designed first and foremost to serve as a general pre-trained
+    model for transfer to specialized tasks. Hence, its "out of the box" or
+    "zero-shot" performance might lag behind models designed specifically for
+    that.
+*   PaliGemma is not a multi-turn chatbot. It is designed for a single round of
+    image and text input.

Paligemma 3B PT 224 gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Paligemma Preprocessor Config.json

@@ -0,0 +1,40 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format",
+    "do_convert_rgb"
+  ],
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "PaliGemmaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

Special Tokens Map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

paligemma-3b-pt-224 config (1).json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "final-hf/paligemma-3b-pt-224-main",
+  "architectures": [
+    "PaliGemmaForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "hidden_size": 2048,
+  "ignore_index": -100,
+  "image_token_index": 257152,
+  "model_type": "paligemma",
+  "pad_token_id": 0,
+  "projection_dim": 2048,
+  "text_config": {
+    "hidden_size": 2048,
+    "intermediate_size": 16384,
+    "model_type": "gemma",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 18,
+    "num_image_tokens": 256,
+    "num_key_value_heads": 1,
+    "torch_dtype": "float32",
+    "vocab_size": 257216
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_image_tokens": 256,
+    "patch_size": 14,
+    "projection_dim": 2048,
+    "projector_hidden_act": "gelu_fast",
+    "vision_use_head": false
+  },
+  "vocab_size": 257216
+}

paligemma-3b-pt-224 config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0.dev0"
+}