update

config.json

@@ -0,0 +1,40 @@
+{
+  "_flash_attn_2_enabled": true,
+  "_name_or_path": "HuatuoGPT-Vision-34B",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "./vit/clip_vit_large_patch14_336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 4096,
+  "tokenizer_padding_side": "left",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eab317fd4627b0fdf39f196aafcfb8a28f763ac4fa919e51f0d9968f6f26a44
+size 4793130760

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a97249daf4da620371066b3d5e1ecb2197cc80ccc760a8aa7e8443b4e83ee938
+size 4756459720

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c0e54b8ab7bf3a0d8954a01fe1e7eeebc1c8771fd6f68375423930009b4314
+size 4991370136

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e065a9f71c12aea53d3b918f9404f19e05d788cd623d397e197c558a6f6ce25
+size 4756459760

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c515b97d42eaf627d1005859cae65488c14c8fdef1ad41f705c12384fc09a761
+size 4756459760

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0d32642cd090e6b5e49da2ba2f35c06ea512eaa55541149c7a7d24481cc52e
+size 4991370160

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64138d45c6cb1aa33d8fbeb1498a9232b920edc60f52d1cd9cd8c75aa2d682e5
+size 4756459760

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4efb9e9bcc36506b60009161926750d002265394444cf063abd3ef2ae6be6c6
+size 4756459760

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe83e40c62fb56c4fdf48dbb44e40426a440f99496563f50b27a8522ad793b3f
+size 4991370160

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beabe77011a34cf1e20b46f8684a55f2f93c98f8956cf53ceef45a4f1638f557
+size 4756459760

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d166674ebc021d7ca6d3a0dfc3f1949d06697c68b70861101cdae16d9ec1edd0
+size 4756459760

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9037cb46032a0d7000a964d7cfd12f653137228ca9ee54a1e81193ff0ea252
+size 4991370160

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1707e1533e9631e3e7dd28eb9b5b9eddca656da9e5f33c65243c68593967ed04
+size 4756459760

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3656c0e44504287543beb26a87838ede6c1df58a7daf300d81c3fe4365049f
+size 4756459760

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ac63c998a08e8e8a14c968df3db524fd22a0fc8b84150c36615bec4d6bdbfd
+size 1935694744

model.safetensors.index.json

@@ -0,0 +1,945 @@
+{
+  "metadata": {
+    "total_size": 69502318592
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.mm_projector.0.bias": "model-00015-of-00015.safetensors",
+    "model.mm_projector.0.weight": "model-00015-of-00015.safetensors",
+    "model.mm_projector.2.bias": "model-00015-of-00015.safetensors",
+    "model.mm_projector.2.weight": "model-00015-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00015-of-00015.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00015-of-00015.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

vit/clip_vit_large_patch14_336/config.json

@@ -0,0 +1,179 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14-336",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.21.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_dim": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.21.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

vit/clip_vit_large_patch14_336/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 336,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 336
+}

vit/clip_vit_large_patch14_336/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6032c2e0caae3dc2d4fba35535fa6307dbb49df59c7e182b1bc4b3329b81801
+size 1711974081

vit/clip_vit_large_patch14_336/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

vit/clip_vit_large_patch14_336/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "do_lower_case": true, "name_or_path": "openai/clip-vit-base-patch32", "model_max_length": 77, "special_tokens_map_file": "/home/suraj/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5", "tokenizer_class": "CLIPTokenizer"}