Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+inference: false
+library_name: transformers
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ja
+- ko
+- zh
+- ar
+- el
+- fa
+- pl
+- id
+- cs
+- he
+- hi
+- nl
+- ro
+- ru
+- tr
+- uk
+- vi
+license: cc-by-nc-4.0
+extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license)  and
+  acknowledge that the information you provide will be collected, used, and shared
+  in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll
+  receive email updates about C4AI and Cohere research, events, products and services.
+  You can unsubscribe at any time.
+extra_gated_fields:
+  Name: text
+  Affiliation: text
+  Country: country
+  I agree to use this model for non-commercial use ONLY: checkbox
+pipeline_tag: image-text-to-text
+tags:
+- mlx
+---
+
+# mlx-community/aya-vision-32b-bf16
+This model was converted to MLX format from [`CohereForAI/aya-vision-32b`]() using mlx-vlm version **0.1.15**.
+Refer to the [original model card](https://huggingface.co/CohereForAI/aya-vision-32b) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/aya-vision-32b-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+```

config.json

@@ -0,0 +1,36 @@
+{
+    "adapter_layer_norm_eps": 1e-06,
+    "alignment_activation_fn": "swiglu",
+    "alignment_intermediate_size": 49152,
+    "architectures": [
+        "AyaVisionForConditionalGeneration"
+    ],
+    "downsample_factor": 2,
+    "image_token_index": 255022,
+    "max_splits_per_img": 12,
+    "model_type": "aya_vision",
+    "projector_hidden_act": "gelu",
+    "text_config": {
+        "intermediate_size": 24576,
+        "model_type": "cohere",
+        "num_key_value_heads": 8,
+        "rope_theta": 4000000,
+        "torch_dtype": "float16",
+        "use_qk_norm": false
+    },
+    "torch_dtype": "float16",
+    "transformers_version": "4.50.0.dev0",
+    "vision_config": {
+        "hidden_size": 1152,
+        "image_size": 364,
+        "intermediate_size": 4304,
+        "model_type": "siglip_vision_model",
+        "num_attention_heads": 16,
+        "num_hidden_layers": 27,
+        "patch_size": 14,
+        "torch_dtype": "float16",
+        "vision_use_head": false
+    },
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "full"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1688c82f05aa5864fc5d7ff641be4651b05c5957aef43f9033d0688b448b2c40
+size 5322207331

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba8ea98db35df0cd8a390b9b12976c77f0d0d6efc8e0cc7fe2fc37d662e3fd5
+size 5335207246

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1f93308702d2a243c0ccc433152a488fccd9f71d66dddb470c1b3fdc3b95c9
+size 5234560858

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a16d8ca65a81523baca04f1cf882d50f31781af125550b1f077fe687a65bc4
+size 5335207250

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a01424c79d71be9bdd2522ae49e3e31408419ab092d8a014267fd1a87a375ed
+size 5234560890

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7111ae954adf4edf9d767af9643e052fc966adf235384422bd7e60d4ced90119
+size 5335207272

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b69fdb37e4c9cc5c923331741e92924fb945289c7828109fc4cf3c427a962ac
+size 5234560882

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df39298c1dd7b0dc23f2b778622c2856bc369183a44fc785804b24c541d563a
+size 5335207272

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3ec886c414e6ffa7941c15b9f7232b016ab65cbe73d97fe7a14b13c56b6faa
+size 5234560892

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e389591f75b3ccf450860c1ba79323c0e0105193336fc42668e106e4a95b456
+size 5335207270

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc022eff70bb592ec106f71591cd2a9b1c82bd670e1e5b557ec7dfed58262a9e
+size 5234560890

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318ce1dd2e2078464b204c8b2564eee1b64cbc5ab601d2a043ac92e40ab6bad2
+size 5335207272

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0961e417fe7a69881901ce964732702aadec2127fe221c4907a4301886a00a
+size 2768424999

model.safetensors.index.json

@@ -0,0 +1,772 @@
+{
+    "metadata": {
+        "total_size": 66274576864
+    },
+    "weight_map": {
+        "language_model.model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "language_model.model.layers.29.input_layernorm.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.29.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.29.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.29.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.29.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "language_model.model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.30.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.30.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.30.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.30.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.31.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+        "language_model.model.layers.32.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.32.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.32.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.32.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.32.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.32.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.32.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.32.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.33.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.33.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.33.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.33.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.33.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.33.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.33.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.33.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.34.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.34.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.34.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.34.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.34.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.34.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.35.input_layernorm.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.35.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.35.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.35.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.35.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.35.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.35.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.35.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "language_model.model.layers.36.input_layernorm.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.36.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.36.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.36.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.36.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.36.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.36.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.36.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.37.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.37.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.37.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.37.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.37.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.37.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.38.input_layernorm.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.38.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.38.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.38.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+        "language_model.model.layers.39.input_layernorm.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.39.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.39.mlp.gate_proj.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.39.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.39.self_attn.k_proj.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.39.self_attn.o_proj.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.39.self_attn.q_proj.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.39.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+        "language_model.model.norm.weight": "model-00013-of-00013.safetensors",
+        "multi_modal_projector.layernorm.bias": "model-00013-of-00013.safetensors",
+        "multi_modal_projector.layernorm.weight": "model-00013-of-00013.safetensors",
+        "multi_modal_projector.linear_1.bias": "model-00013-of-00013.safetensors",
+        "multi_modal_projector.linear_1.weight": "model-00013-of-00013.safetensors",
+        "multi_modal_projector.linear_2.bias": "model-00013-of-00013.safetensors",
+        "multi_modal_projector.linear_2.weight": "model-00013-of-00013.safetensors",
+        "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00013.safetensors",
+        "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00013.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb2974c7ff2633f0dce4490be28531dca552e3ecfafad7a2dfd0e8b212534fc
+size 20124863

tokenizer_config.json

@@ -0,0 +1,356 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_OF_IMG|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_OF_IMG|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|IMG_LINE_BREAK|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|IMG_PATCH|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|EXTRA_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|EXTRA_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|EXTRA_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|EXTRA_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|EXTRA_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255029": {
+      "content": "<|EXTRA_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|EXTRA_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|EXTRA_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<BOS_TOKEN>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{ bos_token }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>You are Aya Vision, a brilliant, sophisticated, AI-assistant chatbot trained to assist human users by providing thorough responses. You are a large vision language model built by the Cohere For AI. You are capable of interpreting images, including describing them, answering questions about their contents, extracting textual information, and analyzing visual context.<|END_OF_TURN_TOKEN|>\n{%- for message in messages -%}\n    <|START_OF_TURN_TOKEN|>{{ message.role | replace(\"user\", \"<|USER_TOKEN|>\") | replace(\"assistant\", \"<|CHATBOT_TOKEN|><|START_RESPONSE|>\") | replace(\"system\", \"<|SYSTEM_TOKEN|>\") }}\n    {%- if message.content is defined -%}\n        {%- if message.content is string -%}\n{{ message.content }}\n        {%- else -%}\n            {%- for item in message.content | selectattr('type', 'equalto', 'image') -%}\n<image>\n            {%- endfor -%}\n            {%- for item in message.content | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n            {%- endfor -%}\n        {%- endif -%}\n    {%- elif message.message is defined -%}\n        {%- if message.message is string -%}\n{{ message.message }}\n        {%- else -%}\n            {%- for item in message.message | selectattr('type', 'equalto', 'image') -%}\n<image>\n            {%- endfor -%}\n            {%- for item in message.message | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n            {%- endfor -%}\n        {%- endif -%}\n    {%- endif -%}\n    {%- if message.role == \"assistant\" -%}\n<|END_RESPONSE|>\n    {%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- endif -%}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "processor_class": "AyaVisionProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}