add model

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "lmsys/vicuna-13b-v1.5",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "connector_depth": 3,
+  "connector_only": false,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "image_position": 35,
+  "image_token_len": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "sva",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_sampler_lr": null,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower_aux_list": [
+    "siglip/CLIP-ViT-SO400M-14-384",
+    "openai/clip-vit-large-patch14-336",
+    "facebook/dinov2-giant-res378",
+    "clip-convnext-XXL-multi-stage"
+  ],
+  "mm_vision_tower_aux_token_len_list": [
+    576,
+    576,
+    576,
+    9216
+  ],
+  "mm_vision_tower_lr": null,
+  "model_type": "llava_llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "num_of_vision_sampler_layers": 10,
+  "num_query_group": 1,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "query_num_list": [
+    576
+  ],
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "spmd_debug": null,
+  "spmd_fsdp_sharding": null,
+  "spmd_mesh": null,
+  "start_of_vision_sampler_layers": 0,
+  "stride_of_vision_sampler_layers": 4,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "tune_mm_mlp_adapter": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vision_hidden_size": 1024,
+  "vision_tower_aux_token_len_list": [
+    576,
+    576,
+    576,
+    9216
+  ],
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c393e287fb564d73d8b3a3fd8624b564120a6f70f1d49a6c249c27ab8f7819
+size 4881272616

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40025b99f6fd631ea1202fd1ff1ee5d8e34771afd94bdd67746a76c47d2321e3
+size 4970418112

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35f0f65bb1c093915107f45074bf015baf6defb0fbef8c05b1bda2f94c08b19
+size 4970418120

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b5e76a9188dffc1d5407857804f11aa9e718e4fb897956210ef88e7a276d63
+size 4970418144

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf60159a87250a478e6bc6b66cdcaf9b68856f9e85a2218ec87bd6176c6b8a1
+size 4970418144

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7038274fedbaa52910e60da96e58afac964e2e536eb629d5ac6b84b70d39397
+size 4792119040

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64770883ef2bef205c52d67a05c16dca490dfd1e52bea863df2c01866b1fb64
+size 4792160232

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc7eb6814c442ea60fae08e7fea1345179a67aba367bc380af6eaf3cc4879dcc
+size 4792160224

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33dee36c1762add540848859bffecb7b22fd9e097b84d7218431ed42a876077
+size 4970418144

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e144f8ef420df21771f670426e67418244850a72af936ff34be06301775fc67
+size 4970418144

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dda3ee7b16361ea9bab918711bceba1074ac329e813a07030553abcabe12468
+size 4320229280

model.safetensors.index.json

@@ -0,0 +1,855 @@
+{
+  "metadata": {
+    "total_size": 53400342528
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00011-of-00011.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
+    "model.image_newline": "model-00001-of-00011.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.mm_projector.0.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector.0.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector.2.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector.2.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_0.2.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_0.2.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_0.3.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_0.3.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_1.2.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_1.2.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_1.3.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_1.3.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_2.2.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_2.2.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_2.3.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_2.3.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_3.2.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_3.2.weight": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_3.3.bias": "model-00011-of-00011.safetensors",
+    "model.mm_projector_aux_3.3.weight": "model-00011-of-00011.safetensors",
+    "model.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_query": "model-00001-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.1.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_0.layers.2.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.0.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.1.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.2.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.3.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.4.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.5.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.6.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.7.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.8.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.k_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.q_proj.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.q_proj.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.q_proj.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_0.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_0.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_0.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_1.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_1.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_1.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_2.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_2.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_2.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_3.0.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_3.0.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.cross_attn.v_proj_3.1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.norm.bias": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.norm.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.pos_embed_3": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.proj_context.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.proj_in.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.proj_out.linear_1.weight": "model-00011-of-00011.safetensors",
+    "model.vision_sampler_layers.9.layers.0.proj_out.linear_2.weight": "model-00011-of-00011.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "<unk>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f6296716ecee2a749ff4bb43f3a86eaef6b3c3bc02024d005ed411fef1597d
+size 5944