Upload VLMForCausalLM

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "uform-gen",
+  "architectures": [
+    "VLMForCausalLM"
+  ],
+  "center_crop": true,
+  "image_encoder_embedding_dim": 256,
+  "image_encoder_hidden_size": 768,
+  "image_encoder_num_heads": 12,
+  "image_encoder_num_layers": 12,
+  "image_encoder_patch_size": 16,
+  "image_encoder_pooling": "cls",
+  "image_pooler_intermediate_size": 5504,
+  "image_pooler_num_attn_heads": 16,
+  "image_pooler_num_latents": 196,
+  "image_size": 224,
+  "image_token_id": 32002,
+  "initializer_range": 0.02,
+  "model_type": "vlm",
+  "text_decoder_name_or_path": "princeton-nlp/Sheared-LLaMA-1.3B",
+  "tokenizer_name_or_path": "uform-gen",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ae42a70765c8dc2d47ed8c5c2cdd7ced413b6d08b58f8983d639b96be87f4b
+size 4984310240

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1bff12925d06fc2207053223358a13175d0b698a78b947154182676266dda7f
+size 973984040

model.safetensors.index.json

@@ -0,0 +1,470 @@
+{
+  "metadata": {
+    "total_size": 5958239744
+  },
+  "weight_map": {
+    "image_encoder.blocks.0.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.attn.key.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.attn.key.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.attn.out.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.attn.out.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.attn.query.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.attn.query.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.attn.value.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.attn.value.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.ls1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.ls2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.cls_token": "model-00002-of-00002.safetensors",
+    "image_encoder.embedding_projection.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.norm.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.norm.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.patch_embed.bias": "model-00002-of-00002.safetensors",
+    "image_encoder.patch_embed.weight": "model-00002-of-00002.safetensors",
+    "image_encoder.pos_embed": "model-00002-of-00002.safetensors",
+    "image_pooler.image_latents": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.linear1.bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.linear1.weight": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.linear2.bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.linear2.weight": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.multihead_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.multihead_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.multihead_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.multihead_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.norm1.bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.norm1.weight": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.norm2.bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.norm2.weight": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.norm3.bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.norm3.weight": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "image_pooler.pooler.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "image_pooler.projection.bias": "model-00002-of-00002.safetensors",
+    "image_pooler.projection.weight": "model-00002-of-00002.safetensors",
+    "text_decoder.lm_head.weight": "model-00002-of-00002.safetensors",
+    "text_decoder.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "text_decoder.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "text_decoder.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "text_decoder.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "text_decoder.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "text_decoder.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_decoder.model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}