Best model up to epoch 0 (val_edit_distance=0.8932019472122192)

.gitattributes

@@ -18,3 +18,19 @@ vanilla/model-00012-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
 vanilla/model-00013-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
 vanilla/model-00014-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
 vanilla/model-00015-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00001-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00002-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00003-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00004-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00005-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00006-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00007-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00008-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00009-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00010-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00011-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00012-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00013-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00014-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/model-00015-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+llava_es-digital-seq/tokenizer.model filter=lfs diff=lfs merge=lfs -text

llava_es-digital-seq/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
     "v_proj",
-    "up_proj",
     "o_proj",
-    "gate_proj",
-    "q_proj"
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj"
   ],
   "task_type": null,
   "use_dora": false,

llava_es-digital-seq/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bfc63e4a6894639428bb2360a6d66b14bbbcfe87d857b4d629359822e55d5e4
+oid sha256:20ea8c39016b3112d61c1e2ae2ecebb0e3a54a5f3d47b6970844dfcef43fd113
 size 84761704

llava_es-digital-seq/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

llava_es-digital-seq/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "llava-hf/llava-1.5-7b-hf",
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_token_index": 32000,
+  "model_type": "llava",
+  "pad_token_id": 32001,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "float16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.2",
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default"
+}

llava_es-digital-seq/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32001,
+  "transformers_version": "4.40.2"
+}

llava_es-digital-seq/model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf16dccf126bcbcc1aee4223e481396357d82924f7742d2a002eb3194817e6ff
+size 978805120

llava_es-digital-seq/model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a3abf4322ec7701080e5f5b9d341aa5a339c5c218ab547fedad434d66df525
+size 966822552

llava_es-digital-seq/model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f88bbbd3d1ddf68212a1929c14fb6c5ca49f6b20725ddaa8f34a7080d6de13
+size 989907728

llava_es-digital-seq/model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568807a9d1df1567550b50ea48a7294fa8b361a5e3f56d7433464437f38ba228
+size 943754008

llava_es-digital-seq/model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b19a2ae4714366727ef1fffa214450bf191675bffe0f123c177e0bb538f8dc3
+size 989891088

llava_es-digital-seq/model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515798cf50c4ab29c92be76cfceca8f288ac23387bf5f153e849b7419927661c
+size 966839208

llava_es-digital-seq/model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7051fea5a4aeb2eadb9cd9446ea003c8d6e3000c90c3035e35ff079ff67607
+size 966822568

llava_es-digital-seq/model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3cc9b855fc69b1323de90666a03958de71a1f11164ce5c0c855e435e6d8af5
+size 989907752

llava_es-digital-seq/model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cb4d227e7f5e18bd4b5443f81efc7b712cb65db333f8950e74fb196808eac6
+size 943754032

llava_es-digital-seq/model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51913c3f4e9b8878a16e88a4e873ea60eb0e34c9b2052168f1a1eaad04f923e
+size 989891104

llava_es-digital-seq/model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c24331fdd0eb088a62ad20e5ad6199a8f8012dc1b80f5bced6ddabed8a1a8bf9
+size 966839208

llava_es-digital-seq/model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3cc0a47954cdd7cc295c74817fb4c4906512bf143b3f6ba52fd8a03d4cd99f8
+size 966822568

llava_es-digital-seq/model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6004bc3f38f251d812181eb4263f641819758047b3680b47a0edf27e738215d3
+size 989907752

llava_es-digital-seq/model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0dceb964e02c3d8f4715bd33e94f9f41011747688659fedf7955f6cf2debda
+size 943754032

llava_es-digital-seq/model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f1e13af4ec6a35c1b79f792148875a806b24cc93ae7fd517b479eb0f56175b7
+size 533226352

llava_es-digital-seq/model.safetensors.index.json

@@ -0,0 +1,693 @@
+{
+  "metadata": {
+    "total_size": 14126854144
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.norm.weight": "model-00015-of-00015.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00015.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00015.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00015.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00015.safetensors"
+  }
+}

llava_es-digital-seq/preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

llava_es-digital-seq/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llava_es-digital-seq/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

llava_es-digital-seq/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}