idefics2-8b-base

added_tokens.json

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

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "Idefics2ForConditionalGeneration"
+  ],
+  "image_token_id": 32001,
+  "model_type": "idefics2",
+  "perceiver_config": {
+    "model_type": "idefics2",
+    "qk_layer_norms": false
+  },
+  "text_config": {
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "vocab_size": 32002
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "idefics2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c7811c3d0085534c037964fa972ecbaa3a274b27f8fceee62b9d14e07a42b9
+size 4644107280

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a5065b73d5073a58524066783a16c19fe9819b9afb70bce47d61f12ae75c8e
+size 4987230248

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2df5c04a61fa240894e21c43b6e2ae1fc39fc7c14685811cb2605f3f910b751
+size 4899116968

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46b45453cfcc9f7b6e9fcb7b4ee94d198b5a14deee6af14380133b940cf393e
+size 4999813704

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167b8a223f1602825e7e5b81d97b4df378d54b88f49a7b7b307dfa55d575d5bc
+size 4999813712

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8c13873d668dd495dcccb7b9c61b0b21e4227e87d4edec367851dccd092fc8
+size 4832008016

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e8b263c2bb5f097b129edc7dcb5850a5c2aaf0e3ecc658a614a038c1960a6a
+size 4249048104

model.safetensors.index.json

@@ -0,0 +1,770 @@
+{
+  "metadata": {
+    "total_size": 33611039680
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.modality_projection.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.modality_projection.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.modality_projection.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.latents": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.input_context_norm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.input_latents_norm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.input_context_norm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.input_latents_norm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.input_context_norm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.input_latents_norm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.perceiver_resampler.norm.weight": "model-00001-of-00007.safetensors",
+    "model.text_model.embed_tokens.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.10.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.10.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.10.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.11.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.11.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.11.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.11.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.11.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.11.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.11.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.11.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.11.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.16.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.text_model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.22.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.text_model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.23.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.text_model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.28.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.28.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.28.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.28.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.28.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.28.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.text_model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.5.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.5.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.5.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.5.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.5.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.5.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.text_model.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.6.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.6.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.6.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.6.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.6.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.6.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.text_model.norm.weight": "model-00007-of-00007.safetensors",
+    "model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.vision_model.post_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.vision_model.post_layernorm.weight": "model-00001-of-00007.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_image_splitting": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Idefics2ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Idefics2Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 980,
+    "shortest_edge": 378
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_len": 64,
+  "processor_class": "Idefics2Processor"
+}

special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<fake_token_around_image>",
+    "<image>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "processor_class": "Idefics2Processor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}