Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)

config.json

@@ -23,7 +23,10 @@
     "quant_method": "awq",
     "version": "gemm",
     "zero_point": true,
-    "modules_to_not_convert": []
+    "modules_to_not_convert": [
+      "model.vision_tower",
+      "model.embed_vision"
+    ]
   },
   "text_config": {
     "attention_bias": false,

model-00002-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ac5993e7999cb66cdb893abfb730b1e1256789b105b95afa559a1e6415e1a7
-size 1985242920
+oid sha256:ac38d5f91e938003295c0f75ff1ea0df8bda728c69fca110c5c910d4d815e802
+size 1997629344

model-00003-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ea3462095b59cf90cd5c9135ed21fd6b2af6c228ee7943eef9ea027e219764
+oid sha256:f25e220b8c6b5978b9bd7a97e69adcc79dd5ecdff4c2b07e662db0f373f9cb91
 size 1996682960

model-00004-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4658a252b61b256a6ca4bbda2887390d58a728f30cc86299104d8018179263
+oid sha256:1bc302c178b3ad5233b03619ef278d3230ba136007d483974e6b084b378b5d4a
 size 2013844744

model-00005-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea19209770b95d7924e9e2195ce510c7636a5d35d3ff7e04902ae7368890fbd
+oid sha256:8e363e7f0aecb9f4dbf0872e3f954af3dd297d7f5dc71b4104b228528cf2d5e3
 size 1982349936

model-00006-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5e555049adc1f6bf7bd6e09e5f9415c08a48770f9c9570841b6ba1d8733b88
+oid sha256:da9242423f41db3463bcda03f9f297b514c68ad6cd1efaaa2b81ba449fce15b1
 size 1959503232

model-00007-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325b29b3ec2bda315c67e2bf5dd7c43605ae2a1defca6746b11c6a642b50633e
+oid sha256:96e01dc901c54f9f6c9aa4cc0b97ec677e3f31b5804d6ffd55f588858a7212e4
 size 1959503248

model-00008-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924b82bfc90607cbac68806346bd87d07247cf1a8b27119d6d6e2f0ff5a75fef
+oid sha256:bcd5ed54a881546502a9f2e97c94edf3cc1ac4ae5e05add2d3b88ada90b9455c
 size 2013833102

model-00009-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c200a14a656e57f8454a1537489f8036aa7db1ba29aed218c7983543ce9c7137
-size 1307285010
+oid sha256:4d6c482642b93b8fc4e35446ae04880e4df0d55141631f8d14eb85d5ac0970af
+size 2003619810

model-00010-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bbcbf73561f6bc5d0a17ea6a2081feed2d1304e87602d8c502d9a5c4bd85576
-size 16
+oid sha256:8d0b96934ff233765527b3456eb8a8bd8cc1eee2d975542abbcfb1fa0ad651b5
+size 442815240

model.safetensors.index.json

@@ -1,9 +1,10 @@
 {
   "metadata": {
-    "total_size": 18036817576
+    "total_size": 19188354024
   },
   "weight_map": {
     "model.language_model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.embed_vision.embedding_projection.weight": "model-00002-of-00010.safetensors",
     "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00010.safetensors",
     "model.language_model.layers.0.layer_scalar": "model-00002-of-00010.safetensors",
     "model.language_model.layers.0.mlp.down_proj.qweight": "model-00002-of-00010.safetensors",
@@ -1654,6 +1655,361 @@
     "model.language_model.layers.59.self_attn.q_proj.qweight": "model-00009-of-00010.safetensors",
     "model.language_model.layers.59.self_attn.q_proj.scales": "model-00009-of-00010.safetensors",
     "model.language_model.layers.59.self_attn.q_proj.qzeros": "model-00009-of-00010.safetensors",
-    "model.language_model.norm.weight": "model-00009-of-00010.safetensors"
+    "model.language_model.norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.mlp.down_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.mlp.up_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.k_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.q_norm.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear.weight": "model-00009-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.mlp.down_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.mlp.up_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.k_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.q_norm.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.patch_embedder.input_proj.weight": "model-00010-of-00010.safetensors",
+    "model.vision_tower.patch_embedder.position_embedding_table": "model-00010-of-00010.safetensors",
+    "model.vision_tower.std_bias": "model-00010-of-00010.safetensors",
+    "model.vision_tower.std_scale": "model-00010-of-00010.safetensors"
   }
 }