Upload CLIPT5ForConditionalGeneration

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "zhiqiulin/clip-flant5-xxl",
+  "architectures": [
+    "CLIPT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "freeze_mm_mlp_adapter": false,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "mm_hidden_size": 1024,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "clip_t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_hidden_states": true,
+  "output_past": true,
+  "pad_token_id": 0,
+  "prefix_mask": false,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e14a89e6eff8b99ca0732a533d2d969ac20e496634a4168dc1cb6a7444eee1
+size 4989332434

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f100e77728a9d9cf63b22ec108dcadfb614a4b1248ed82c3c61a91254127782
+size 4999844240

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa68cf28c5e85349a0abd16054324ee156eca200a55634f384b6ee49a2fd7a3e
+size 4865625836

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4ea8efe2cd191c5e69d698ccc4a770f9a06e6355fee8301727849a3407872c
+size 4899206172

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c62227cdccd81fef3a1cdc95f09c9ebcc6bcb9e40a76cca6af3747f849ce4c
+size 4966309020

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9b30916fd272376b14180be74cd0409b21106ad204ca1af737003a07e2efe7
+size 4999879748

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32b15f152f97a085b6ac6e29a16ac1dd8c0d2caf0d416f01843cfcbd27aeb52
+size 4994806054

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9007c9fc8b7ceb66dc16ab6ff038dbafa1719dd1bc938d223c1b02e7bef16982
+size 722204970

pytorch_model.bin.index.json

@@ -0,0 +1,823 @@
+{
+  "metadata": {
+    "total_size": 35436912640
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "lm_head.weight": "pytorch_model-00007-of-00008.bin",
+    "mm_projector.0.bias": "pytorch_model-00008-of-00008.bin",
+    "mm_projector.0.weight": "pytorch_model-00008-of-00008.bin",
+    "mm_projector.2.bias": "pytorch_model-00008-of-00008.bin",
+    "mm_projector.2.weight": "pytorch_model-00008-of-00008.bin",
+    "shared.weight": "pytorch_model-00001-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00007-of-00008.bin",
+    "vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00007-of-00008.bin"
+  }
+}