Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 100353,
+  "<s>": 100352
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "AriaForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "modeling_aria.AriaConfig",
+    "AutoModelForCausalLM": "modeling_aria.AriaForConditionalGeneration"
+  },
+  "ignore_index": -100,
+  "image_token_index": 9,
+  "model_type": "aria",
+  "projector_patch_to_query_dict": {
+    "1225": 128,
+    "4900": 256
+  },
+  "text_config": {
+    "hidden_size": 2560,
+    "intermediate_size": 13568,
+    "max_position_embeddings": 65536,
+    "model_type": "aria_moe_lm",
+    "moe_grouped_gemm": true,
+    "moe_intermediate_size": 1664,
+    "moe_num_experts": 64,
+    "moe_topk": 6,
+    "num_attention_heads": 20,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 20,
+    "rope_theta": 5000000,
+    "vocab_size": 100352
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "vision_config": {
+    "_flash_attn_2_enabled": true,
+    "architectures": [
+      "AriaVisionModel"
+    ],
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "aria_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16"
+  }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a08b65dd8d0f83d0e3a55891dbf9e74fcc3f04aeb95689c6504f0c2c217027b
+size 4922385968

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf398930670adec8c16d7c8a5b6e4ef02760eba3913c5852bb4c4b3e160ff0a8
+size 4569849136

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb49c11ba7d81c985a6e1c98f2f345d188b1dcec752033a4800ed5f1cef2e39d
+size 4128475752

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080f33a162c2a10d2d6e79f4fb72741a232f8f626e180c355b4670c5c6e2323c
+size 4569849136

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa1881298967e93f54e96ee8a7745ffd137ba370dee4a15cb00ca8b47d9114b
+size 4128475792

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc2a036e4fe0ebb08556677bfa5005fc35665ac5e86d16e245ecc4f0d651ca7
+size 4569849160

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74dfd4f95071433a245b014b8dfb92877a76ae426e629f70efbd909e7017f3f
+size 4128475784

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ece1d0f7668848297b24c35502f3f000be25209bd993723c6a8141932744ec5
+size 4569849160

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a14959180c8fa1c3148a7739777b0f103169b1f6dd0d9e3b1fbcd25069ec5a
+size 4128475784

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2c93037fb093b7df0eb9130613f8ca2362ec5eb085c9fe8e7550343c66296b
+size 4569849160

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5030c603d44d6c4f03d3051617bbb4ac3c69a9c801f743f9c07d143760bc4d5e
+size 4128475784

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ae42e70280f701880d073e4e9b52cb1f48fb9c1279d9060fac3b856ebe2993
+size 2200715456

model.safetensors.index.json

@@ -0,0 +1,799 @@
+{
+  "metadata": {
+    "total_size": 50614617824
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.experts.fc1.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.experts.fc2.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.router.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.shared_experts.down_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.shared_experts.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.shared_experts.up_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.experts.fc1.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.experts.fc2.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.router.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.experts.fc1.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.experts.fc2.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.router.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.shared_experts.down_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.shared_experts.up_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.experts.fc1.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.experts.fc2.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.router.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.shared_experts.down_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.shared_experts.up_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.experts.fc1.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.experts.fc2.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.router.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.shared_experts.down_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.shared_experts.up_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.experts.fc1.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.experts.fc2.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.router.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.shared_experts.down_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.shared_experts.up_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.experts.fc1.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.experts.fc2.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.router.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.shared_experts.down_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.shared_experts.up_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.experts.fc1.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.experts.fc2.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.router.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.shared_experts.down_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.shared_experts.up_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.experts.fc1.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.experts.fc2.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.router.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.shared_experts.down_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.shared_experts.up_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.experts.fc1.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.experts.fc2.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.router.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.shared_experts.down_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.shared_experts.up_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.experts.fc1.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.experts.fc2.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.router.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.shared_experts.down_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.shared_experts.up_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.experts.fc1.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.experts.fc2.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.router.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.shared_experts.down_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.shared_experts.up_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.experts.fc1.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.experts.fc2.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.router.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.shared_experts.down_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.shared_experts.up_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.experts.fc1.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.experts.fc2.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.router.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.shared_experts.down_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.shared_experts.up_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.experts.fc1.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.experts.fc2.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.router.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.shared_experts.down_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.shared_experts.up_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.experts.fc1.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.experts.fc2.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.router.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.shared_experts.down_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.shared_experts.up_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.experts.fc1.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.experts.fc2.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.router.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.shared_experts.down_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.shared_experts.up_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.experts.fc1.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.experts.fc2.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.router.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.shared_experts.down_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.shared_experts.up_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.experts.fc1.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.experts.fc2.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.router.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.shared_experts.down_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.shared_experts.up_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.experts.fc1.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.experts.fc2.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.router.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.shared_experts.down_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.shared_experts.up_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.experts.fc1.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.experts.fc2.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.router.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.shared_experts.down_proj.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.shared_experts.up_proj.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.experts.fc1.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.experts.fc2.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.router.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.shared_experts.down_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.shared_experts.up_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.experts.fc1.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.experts.fc2.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.router.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.shared_experts.down_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.shared_experts.up_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.experts.fc1.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.experts.fc2.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.router.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.shared_experts.down_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.shared_experts.up_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.experts.fc1.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.experts.fc2.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.router.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.shared_experts.down_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.shared_experts.up_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.experts.fc1.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.experts.fc2.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.router.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.shared_experts.down_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.shared_experts.up_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.experts.fc1.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.experts.fc2.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.router.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.shared_experts.down_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.shared_experts.up_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.experts.fc1.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.experts.fc2.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.router.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.shared_experts.down_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.shared_experts.up_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.norm.weight": "model-00012-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.layer_norm.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.layer_norm.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.linear.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.linear.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.ln_kv.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.ln_kv.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.multihead_attn.in_proj_bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.multihead_attn.in_proj_weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.multihead_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.multihead_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.ffn.linear_in.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.ffn.linear_out.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.ln_ffn.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.ln_ffn.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.query": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00012.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e429a008ed1045d14464933311e0b3258575980efc9db4e61f368e399c719d2a
+size 1696299

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100352": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100353": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}