diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" --- "a/model.safetensors.index.json" +++ "b/model.safetensors.index.json" @@ -1,6 +1,6 @@ { "metadata": { - "total_size": 110762564784 + "total_size": 111650237920 }, "weight_map": { "language_model.lm_head.weight": "model-00026-of-00026.safetensors", @@ -8,12 +8,13 @@ "language_model.model.layers.0.feed_forward.experts.down_proj.SCB": "model-00002-of-00026.safetensors", "language_model.model.layers.0.feed_forward.experts.down_proj.weight": "model-00002-of-00026.safetensors", "language_model.model.layers.0.feed_forward.experts.down_proj.weight_format": "model-00002-of-00026.safetensors", - "language_model.model.layers.0.feed_forward.experts.gate_up_proj.SCB": "model-00001-of-00026.safetensors", - "language_model.model.layers.0.feed_forward.experts.gate_up_proj.weight": "model-00001-of-00026.safetensors", - "language_model.model.layers.0.feed_forward.experts.gate_up_proj.weight_format": "model-00001-of-00026.safetensors", - "language_model.model.layers.0.feed_forward.router.SCB": "model-00002-of-00026.safetensors", + "language_model.model.layers.0.feed_forward.experts.gate_proj.SCB": "model-00001-of-00026.safetensors", + "language_model.model.layers.0.feed_forward.experts.gate_proj.weight": "model-00001-of-00026.safetensors", + "language_model.model.layers.0.feed_forward.experts.gate_proj.weight_format": "model-00001-of-00026.safetensors", + "language_model.model.layers.0.feed_forward.experts.up_proj.SCB": "model-00002-of-00026.safetensors", + "language_model.model.layers.0.feed_forward.experts.up_proj.weight": "model-00002-of-00026.safetensors", + "language_model.model.layers.0.feed_forward.experts.up_proj.weight_format": "model-00002-of-00026.safetensors", "language_model.model.layers.0.feed_forward.router.weight": "model-00002-of-00026.safetensors", - "language_model.model.layers.0.feed_forward.router.weight_format": "model-00002-of-00026.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.down_proj.SCB": "model-00002-of-00026.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.down_proj.weight": "model-00002-of-00026.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.down_proj.weight_format": "model-00002-of-00026.safetensors", @@ -40,12 +41,13 @@ "language_model.model.layers.1.feed_forward.experts.down_proj.SCB": "model-00002-of-00026.safetensors", "language_model.model.layers.1.feed_forward.experts.down_proj.weight": "model-00002-of-00026.safetensors", "language_model.model.layers.1.feed_forward.experts.down_proj.weight_format": "model-00002-of-00026.safetensors", - "language_model.model.layers.1.feed_forward.experts.gate_up_proj.SCB": "model-00002-of-00026.safetensors", - "language_model.model.layers.1.feed_forward.experts.gate_up_proj.weight": "model-00002-of-00026.safetensors", - "language_model.model.layers.1.feed_forward.experts.gate_up_proj.weight_format": "model-00002-of-00026.safetensors", - "language_model.model.layers.1.feed_forward.router.SCB": "model-00002-of-00026.safetensors", + "language_model.model.layers.1.feed_forward.experts.gate_proj.SCB": "model-00002-of-00026.safetensors", + "language_model.model.layers.1.feed_forward.experts.gate_proj.weight": "model-00002-of-00026.safetensors", + "language_model.model.layers.1.feed_forward.experts.gate_proj.weight_format": "model-00002-of-00026.safetensors", + "language_model.model.layers.1.feed_forward.experts.up_proj.SCB": "model-00002-of-00026.safetensors", + "language_model.model.layers.1.feed_forward.experts.up_proj.weight": "model-00002-of-00026.safetensors", + "language_model.model.layers.1.feed_forward.experts.up_proj.weight_format": "model-00002-of-00026.safetensors", "language_model.model.layers.1.feed_forward.router.weight": "model-00002-of-00026.safetensors", - "language_model.model.layers.1.feed_forward.router.weight_format": "model-00002-of-00026.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.down_proj.SCB": "model-00002-of-00026.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.down_proj.weight": "model-00002-of-00026.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.down_proj.weight_format": "model-00002-of-00026.safetensors", @@ -72,12 +74,13 @@ "language_model.model.layers.10.feed_forward.experts.down_proj.SCB": "model-00007-of-00026.safetensors", "language_model.model.layers.10.feed_forward.experts.down_proj.weight": "model-00007-of-00026.safetensors", "language_model.model.layers.10.feed_forward.experts.down_proj.weight_format": "model-00007-of-00026.safetensors", - "language_model.model.layers.10.feed_forward.experts.gate_up_proj.SCB": "model-00006-of-00026.safetensors", - "language_model.model.layers.10.feed_forward.experts.gate_up_proj.weight": "model-00006-of-00026.safetensors", - "language_model.model.layers.10.feed_forward.experts.gate_up_proj.weight_format": "model-00006-of-00026.safetensors", - "language_model.model.layers.10.feed_forward.router.SCB": "model-00007-of-00026.safetensors", + "language_model.model.layers.10.feed_forward.experts.gate_proj.SCB": "model-00006-of-00026.safetensors", + "language_model.model.layers.10.feed_forward.experts.gate_proj.weight": "model-00006-of-00026.safetensors", + "language_model.model.layers.10.feed_forward.experts.gate_proj.weight_format": "model-00006-of-00026.safetensors", + "language_model.model.layers.10.feed_forward.experts.up_proj.SCB": "model-00007-of-00026.safetensors", + "language_model.model.layers.10.feed_forward.experts.up_proj.weight": "model-00007-of-00026.safetensors", + "language_model.model.layers.10.feed_forward.experts.up_proj.weight_format": "model-00007-of-00026.safetensors", "language_model.model.layers.10.feed_forward.router.weight": "model-00007-of-00026.safetensors", - "language_model.model.layers.10.feed_forward.router.weight_format": "model-00007-of-00026.safetensors", "language_model.model.layers.10.feed_forward.shared_expert.down_proj.SCB": "model-00007-of-00026.safetensors", "language_model.model.layers.10.feed_forward.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors", "language_model.model.layers.10.feed_forward.shared_expert.down_proj.weight_format": "model-00007-of-00026.safetensors", @@ -104,12 +107,13 @@ "language_model.model.layers.11.feed_forward.experts.down_proj.SCB": "model-00007-of-00026.safetensors", "language_model.model.layers.11.feed_forward.experts.down_proj.weight": "model-00007-of-00026.safetensors", "language_model.model.layers.11.feed_forward.experts.down_proj.weight_format": "model-00007-of-00026.safetensors", - "language_model.model.layers.11.feed_forward.experts.gate_up_proj.SCB": "model-00007-of-00026.safetensors", - "language_model.model.layers.11.feed_forward.experts.gate_up_proj.weight": "model-00007-of-00026.safetensors", - "language_model.model.layers.11.feed_forward.experts.gate_up_proj.weight_format": "model-00007-of-00026.safetensors", - "language_model.model.layers.11.feed_forward.router.SCB": "model-00007-of-00026.safetensors", + "language_model.model.layers.11.feed_forward.experts.gate_proj.SCB": "model-00007-of-00026.safetensors", + "language_model.model.layers.11.feed_forward.experts.gate_proj.weight": "model-00007-of-00026.safetensors", + "language_model.model.layers.11.feed_forward.experts.gate_proj.weight_format": "model-00007-of-00026.safetensors", + "language_model.model.layers.11.feed_forward.experts.up_proj.SCB": "model-00007-of-00026.safetensors", + "language_model.model.layers.11.feed_forward.experts.up_proj.weight": "model-00007-of-00026.safetensors", + "language_model.model.layers.11.feed_forward.experts.up_proj.weight_format": "model-00007-of-00026.safetensors", "language_model.model.layers.11.feed_forward.router.weight": "model-00007-of-00026.safetensors", - "language_model.model.layers.11.feed_forward.router.weight_format": "model-00007-of-00026.safetensors", "language_model.model.layers.11.feed_forward.shared_expert.down_proj.SCB": "model-00007-of-00026.safetensors", "language_model.model.layers.11.feed_forward.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors", "language_model.model.layers.11.feed_forward.shared_expert.down_proj.weight_format": "model-00007-of-00026.safetensors", @@ -136,12 +140,13 @@ "language_model.model.layers.12.feed_forward.experts.down_proj.SCB": "model-00008-of-00026.safetensors", "language_model.model.layers.12.feed_forward.experts.down_proj.weight": "model-00008-of-00026.safetensors", "language_model.model.layers.12.feed_forward.experts.down_proj.weight_format": "model-00008-of-00026.safetensors", - "language_model.model.layers.12.feed_forward.experts.gate_up_proj.SCB": "model-00007-of-00026.safetensors", - "language_model.model.layers.12.feed_forward.experts.gate_up_proj.weight": "model-00007-of-00026.safetensors", - "language_model.model.layers.12.feed_forward.experts.gate_up_proj.weight_format": "model-00007-of-00026.safetensors", - "language_model.model.layers.12.feed_forward.router.SCB": "model-00008-of-00026.safetensors", + "language_model.model.layers.12.feed_forward.experts.gate_proj.SCB": "model-00007-of-00026.safetensors", + "language_model.model.layers.12.feed_forward.experts.gate_proj.weight": "model-00007-of-00026.safetensors", + "language_model.model.layers.12.feed_forward.experts.gate_proj.weight_format": "model-00007-of-00026.safetensors", + "language_model.model.layers.12.feed_forward.experts.up_proj.SCB": "model-00008-of-00026.safetensors", + "language_model.model.layers.12.feed_forward.experts.up_proj.weight": "model-00008-of-00026.safetensors", + "language_model.model.layers.12.feed_forward.experts.up_proj.weight_format": "model-00008-of-00026.safetensors", "language_model.model.layers.12.feed_forward.router.weight": "model-00008-of-00026.safetensors", - "language_model.model.layers.12.feed_forward.router.weight_format": "model-00008-of-00026.safetensors", "language_model.model.layers.12.feed_forward.shared_expert.down_proj.SCB": "model-00008-of-00026.safetensors", "language_model.model.layers.12.feed_forward.shared_expert.down_proj.weight": "model-00008-of-00026.safetensors", "language_model.model.layers.12.feed_forward.shared_expert.down_proj.weight_format": "model-00008-of-00026.safetensors", @@ -168,12 +173,13 @@ "language_model.model.layers.13.feed_forward.experts.down_proj.SCB": "model-00008-of-00026.safetensors", "language_model.model.layers.13.feed_forward.experts.down_proj.weight": "model-00008-of-00026.safetensors", "language_model.model.layers.13.feed_forward.experts.down_proj.weight_format": "model-00008-of-00026.safetensors", - "language_model.model.layers.13.feed_forward.experts.gate_up_proj.SCB": "model-00008-of-00026.safetensors", - "language_model.model.layers.13.feed_forward.experts.gate_up_proj.weight": "model-00008-of-00026.safetensors", - "language_model.model.layers.13.feed_forward.experts.gate_up_proj.weight_format": "model-00008-of-00026.safetensors", - "language_model.model.layers.13.feed_forward.router.SCB": "model-00008-of-00026.safetensors", + "language_model.model.layers.13.feed_forward.experts.gate_proj.SCB": "model-00008-of-00026.safetensors", + "language_model.model.layers.13.feed_forward.experts.gate_proj.weight": "model-00008-of-00026.safetensors", + "language_model.model.layers.13.feed_forward.experts.gate_proj.weight_format": "model-00008-of-00026.safetensors", + "language_model.model.layers.13.feed_forward.experts.up_proj.SCB": "model-00008-of-00026.safetensors", + "language_model.model.layers.13.feed_forward.experts.up_proj.weight": "model-00008-of-00026.safetensors", + "language_model.model.layers.13.feed_forward.experts.up_proj.weight_format": "model-00008-of-00026.safetensors", "language_model.model.layers.13.feed_forward.router.weight": "model-00008-of-00026.safetensors", - "language_model.model.layers.13.feed_forward.router.weight_format": "model-00008-of-00026.safetensors", "language_model.model.layers.13.feed_forward.shared_expert.down_proj.SCB": "model-00008-of-00026.safetensors", "language_model.model.layers.13.feed_forward.shared_expert.down_proj.weight": "model-00008-of-00026.safetensors", "language_model.model.layers.13.feed_forward.shared_expert.down_proj.weight_format": "model-00008-of-00026.safetensors", @@ -200,12 +206,13 @@ "language_model.model.layers.14.feed_forward.experts.down_proj.SCB": "model-00009-of-00026.safetensors", "language_model.model.layers.14.feed_forward.experts.down_proj.weight": "model-00009-of-00026.safetensors", "language_model.model.layers.14.feed_forward.experts.down_proj.weight_format": "model-00009-of-00026.safetensors", - "language_model.model.layers.14.feed_forward.experts.gate_up_proj.SCB": "model-00008-of-00026.safetensors", - "language_model.model.layers.14.feed_forward.experts.gate_up_proj.weight": "model-00008-of-00026.safetensors", - "language_model.model.layers.14.feed_forward.experts.gate_up_proj.weight_format": "model-00008-of-00026.safetensors", - "language_model.model.layers.14.feed_forward.router.SCB": "model-00009-of-00026.safetensors", + "language_model.model.layers.14.feed_forward.experts.gate_proj.SCB": "model-00008-of-00026.safetensors", + "language_model.model.layers.14.feed_forward.experts.gate_proj.weight": "model-00008-of-00026.safetensors", + "language_model.model.layers.14.feed_forward.experts.gate_proj.weight_format": "model-00008-of-00026.safetensors", + "language_model.model.layers.14.feed_forward.experts.up_proj.SCB": "model-00009-of-00026.safetensors", + "language_model.model.layers.14.feed_forward.experts.up_proj.weight": "model-00009-of-00026.safetensors", + "language_model.model.layers.14.feed_forward.experts.up_proj.weight_format": "model-00009-of-00026.safetensors", "language_model.model.layers.14.feed_forward.router.weight": "model-00009-of-00026.safetensors", - "language_model.model.layers.14.feed_forward.router.weight_format": "model-00009-of-00026.safetensors", "language_model.model.layers.14.feed_forward.shared_expert.down_proj.SCB": "model-00009-of-00026.safetensors", "language_model.model.layers.14.feed_forward.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors", "language_model.model.layers.14.feed_forward.shared_expert.down_proj.weight_format": "model-00009-of-00026.safetensors", @@ -232,12 +239,13 @@ "language_model.model.layers.15.feed_forward.experts.down_proj.SCB": "model-00009-of-00026.safetensors", "language_model.model.layers.15.feed_forward.experts.down_proj.weight": "model-00009-of-00026.safetensors", "language_model.model.layers.15.feed_forward.experts.down_proj.weight_format": "model-00009-of-00026.safetensors", - "language_model.model.layers.15.feed_forward.experts.gate_up_proj.SCB": "model-00009-of-00026.safetensors", - "language_model.model.layers.15.feed_forward.experts.gate_up_proj.weight": "model-00009-of-00026.safetensors", - "language_model.model.layers.15.feed_forward.experts.gate_up_proj.weight_format": "model-00009-of-00026.safetensors", - "language_model.model.layers.15.feed_forward.router.SCB": "model-00009-of-00026.safetensors", + "language_model.model.layers.15.feed_forward.experts.gate_proj.SCB": "model-00009-of-00026.safetensors", + "language_model.model.layers.15.feed_forward.experts.gate_proj.weight": "model-00009-of-00026.safetensors", + "language_model.model.layers.15.feed_forward.experts.gate_proj.weight_format": "model-00009-of-00026.safetensors", + "language_model.model.layers.15.feed_forward.experts.up_proj.SCB": "model-00009-of-00026.safetensors", + "language_model.model.layers.15.feed_forward.experts.up_proj.weight": "model-00009-of-00026.safetensors", + "language_model.model.layers.15.feed_forward.experts.up_proj.weight_format": "model-00009-of-00026.safetensors", "language_model.model.layers.15.feed_forward.router.weight": "model-00009-of-00026.safetensors", - "language_model.model.layers.15.feed_forward.router.weight_format": "model-00009-of-00026.safetensors", "language_model.model.layers.15.feed_forward.shared_expert.down_proj.SCB": "model-00009-of-00026.safetensors", "language_model.model.layers.15.feed_forward.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors", "language_model.model.layers.15.feed_forward.shared_expert.down_proj.weight_format": "model-00009-of-00026.safetensors", @@ -264,12 +272,13 @@ "language_model.model.layers.16.feed_forward.experts.down_proj.SCB": "model-00010-of-00026.safetensors", "language_model.model.layers.16.feed_forward.experts.down_proj.weight": "model-00010-of-00026.safetensors", "language_model.model.layers.16.feed_forward.experts.down_proj.weight_format": "model-00010-of-00026.safetensors", - "language_model.model.layers.16.feed_forward.experts.gate_up_proj.SCB": "model-00009-of-00026.safetensors", - "language_model.model.layers.16.feed_forward.experts.gate_up_proj.weight": "model-00009-of-00026.safetensors", - "language_model.model.layers.16.feed_forward.experts.gate_up_proj.weight_format": "model-00009-of-00026.safetensors", - "language_model.model.layers.16.feed_forward.router.SCB": "model-00010-of-00026.safetensors", + "language_model.model.layers.16.feed_forward.experts.gate_proj.SCB": "model-00009-of-00026.safetensors", + "language_model.model.layers.16.feed_forward.experts.gate_proj.weight": "model-00009-of-00026.safetensors", + "language_model.model.layers.16.feed_forward.experts.gate_proj.weight_format": "model-00009-of-00026.safetensors", + "language_model.model.layers.16.feed_forward.experts.up_proj.SCB": "model-00010-of-00026.safetensors", + "language_model.model.layers.16.feed_forward.experts.up_proj.weight": "model-00010-of-00026.safetensors", + "language_model.model.layers.16.feed_forward.experts.up_proj.weight_format": "model-00010-of-00026.safetensors", "language_model.model.layers.16.feed_forward.router.weight": "model-00010-of-00026.safetensors", - "language_model.model.layers.16.feed_forward.router.weight_format": "model-00010-of-00026.safetensors", "language_model.model.layers.16.feed_forward.shared_expert.down_proj.SCB": "model-00010-of-00026.safetensors", "language_model.model.layers.16.feed_forward.shared_expert.down_proj.weight": "model-00010-of-00026.safetensors", "language_model.model.layers.16.feed_forward.shared_expert.down_proj.weight_format": "model-00010-of-00026.safetensors", @@ -296,12 +305,13 @@ "language_model.model.layers.17.feed_forward.experts.down_proj.SCB": "model-00010-of-00026.safetensors", "language_model.model.layers.17.feed_forward.experts.down_proj.weight": "model-00010-of-00026.safetensors", "language_model.model.layers.17.feed_forward.experts.down_proj.weight_format": "model-00010-of-00026.safetensors", - "language_model.model.layers.17.feed_forward.experts.gate_up_proj.SCB": "model-00010-of-00026.safetensors", - "language_model.model.layers.17.feed_forward.experts.gate_up_proj.weight": "model-00010-of-00026.safetensors", - "language_model.model.layers.17.feed_forward.experts.gate_up_proj.weight_format": "model-00010-of-00026.safetensors", - "language_model.model.layers.17.feed_forward.router.SCB": "model-00010-of-00026.safetensors", + "language_model.model.layers.17.feed_forward.experts.gate_proj.SCB": "model-00010-of-00026.safetensors", + "language_model.model.layers.17.feed_forward.experts.gate_proj.weight": "model-00010-of-00026.safetensors", + "language_model.model.layers.17.feed_forward.experts.gate_proj.weight_format": "model-00010-of-00026.safetensors", + "language_model.model.layers.17.feed_forward.experts.up_proj.SCB": "model-00010-of-00026.safetensors", + "language_model.model.layers.17.feed_forward.experts.up_proj.weight": "model-00010-of-00026.safetensors", + "language_model.model.layers.17.feed_forward.experts.up_proj.weight_format": "model-00010-of-00026.safetensors", "language_model.model.layers.17.feed_forward.router.weight": "model-00010-of-00026.safetensors", - "language_model.model.layers.17.feed_forward.router.weight_format": "model-00010-of-00026.safetensors", "language_model.model.layers.17.feed_forward.shared_expert.down_proj.SCB": "model-00010-of-00026.safetensors", "language_model.model.layers.17.feed_forward.shared_expert.down_proj.weight": "model-00010-of-00026.safetensors", "language_model.model.layers.17.feed_forward.shared_expert.down_proj.weight_format": "model-00010-of-00026.safetensors", @@ -328,12 +338,13 @@ "language_model.model.layers.18.feed_forward.experts.down_proj.SCB": "model-00011-of-00026.safetensors", "language_model.model.layers.18.feed_forward.experts.down_proj.weight": "model-00011-of-00026.safetensors", "language_model.model.layers.18.feed_forward.experts.down_proj.weight_format": "model-00011-of-00026.safetensors", - "language_model.model.layers.18.feed_forward.experts.gate_up_proj.SCB": "model-00010-of-00026.safetensors", - "language_model.model.layers.18.feed_forward.experts.gate_up_proj.weight": "model-00010-of-00026.safetensors", - "language_model.model.layers.18.feed_forward.experts.gate_up_proj.weight_format": "model-00010-of-00026.safetensors", - "language_model.model.layers.18.feed_forward.router.SCB": "model-00011-of-00026.safetensors", + "language_model.model.layers.18.feed_forward.experts.gate_proj.SCB": "model-00010-of-00026.safetensors", + "language_model.model.layers.18.feed_forward.experts.gate_proj.weight": "model-00010-of-00026.safetensors", + "language_model.model.layers.18.feed_forward.experts.gate_proj.weight_format": "model-00010-of-00026.safetensors", + "language_model.model.layers.18.feed_forward.experts.up_proj.SCB": "model-00011-of-00026.safetensors", + "language_model.model.layers.18.feed_forward.experts.up_proj.weight": "model-00011-of-00026.safetensors", + "language_model.model.layers.18.feed_forward.experts.up_proj.weight_format": "model-00011-of-00026.safetensors", "language_model.model.layers.18.feed_forward.router.weight": "model-00011-of-00026.safetensors", - "language_model.model.layers.18.feed_forward.router.weight_format": "model-00011-of-00026.safetensors", "language_model.model.layers.18.feed_forward.shared_expert.down_proj.SCB": "model-00011-of-00026.safetensors", "language_model.model.layers.18.feed_forward.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors", "language_model.model.layers.18.feed_forward.shared_expert.down_proj.weight_format": "model-00011-of-00026.safetensors", @@ -360,12 +371,13 @@ "language_model.model.layers.19.feed_forward.experts.down_proj.SCB": "model-00011-of-00026.safetensors", "language_model.model.layers.19.feed_forward.experts.down_proj.weight": "model-00011-of-00026.safetensors", "language_model.model.layers.19.feed_forward.experts.down_proj.weight_format": "model-00011-of-00026.safetensors", - "language_model.model.layers.19.feed_forward.experts.gate_up_proj.SCB": "model-00011-of-00026.safetensors", - "language_model.model.layers.19.feed_forward.experts.gate_up_proj.weight": "model-00011-of-00026.safetensors", - "language_model.model.layers.19.feed_forward.experts.gate_up_proj.weight_format": "model-00011-of-00026.safetensors", - "language_model.model.layers.19.feed_forward.router.SCB": "model-00011-of-00026.safetensors", + "language_model.model.layers.19.feed_forward.experts.gate_proj.SCB": "model-00011-of-00026.safetensors", + "language_model.model.layers.19.feed_forward.experts.gate_proj.weight": "model-00011-of-00026.safetensors", + "language_model.model.layers.19.feed_forward.experts.gate_proj.weight_format": "model-00011-of-00026.safetensors", + "language_model.model.layers.19.feed_forward.experts.up_proj.SCB": "model-00011-of-00026.safetensors", + "language_model.model.layers.19.feed_forward.experts.up_proj.weight": "model-00011-of-00026.safetensors", + "language_model.model.layers.19.feed_forward.experts.up_proj.weight_format": "model-00011-of-00026.safetensors", "language_model.model.layers.19.feed_forward.router.weight": "model-00011-of-00026.safetensors", - "language_model.model.layers.19.feed_forward.router.weight_format": "model-00011-of-00026.safetensors", "language_model.model.layers.19.feed_forward.shared_expert.down_proj.SCB": "model-00011-of-00026.safetensors", "language_model.model.layers.19.feed_forward.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors", "language_model.model.layers.19.feed_forward.shared_expert.down_proj.weight_format": "model-00011-of-00026.safetensors", @@ -392,12 +404,13 @@ "language_model.model.layers.2.feed_forward.experts.down_proj.SCB": "model-00003-of-00026.safetensors", "language_model.model.layers.2.feed_forward.experts.down_proj.weight": "model-00003-of-00026.safetensors", "language_model.model.layers.2.feed_forward.experts.down_proj.weight_format": "model-00003-of-00026.safetensors", - "language_model.model.layers.2.feed_forward.experts.gate_up_proj.SCB": "model-00002-of-00026.safetensors", - "language_model.model.layers.2.feed_forward.experts.gate_up_proj.weight": "model-00002-of-00026.safetensors", - "language_model.model.layers.2.feed_forward.experts.gate_up_proj.weight_format": "model-00002-of-00026.safetensors", - "language_model.model.layers.2.feed_forward.router.SCB": "model-00003-of-00026.safetensors", + "language_model.model.layers.2.feed_forward.experts.gate_proj.SCB": "model-00002-of-00026.safetensors", + "language_model.model.layers.2.feed_forward.experts.gate_proj.weight": "model-00002-of-00026.safetensors", + "language_model.model.layers.2.feed_forward.experts.gate_proj.weight_format": "model-00002-of-00026.safetensors", + "language_model.model.layers.2.feed_forward.experts.up_proj.SCB": "model-00003-of-00026.safetensors", + "language_model.model.layers.2.feed_forward.experts.up_proj.weight": "model-00003-of-00026.safetensors", + "language_model.model.layers.2.feed_forward.experts.up_proj.weight_format": "model-00003-of-00026.safetensors", "language_model.model.layers.2.feed_forward.router.weight": "model-00003-of-00026.safetensors", - "language_model.model.layers.2.feed_forward.router.weight_format": "model-00003-of-00026.safetensors", "language_model.model.layers.2.feed_forward.shared_expert.down_proj.SCB": "model-00003-of-00026.safetensors", "language_model.model.layers.2.feed_forward.shared_expert.down_proj.weight": "model-00003-of-00026.safetensors", "language_model.model.layers.2.feed_forward.shared_expert.down_proj.weight_format": "model-00003-of-00026.safetensors", @@ -424,12 +437,13 @@ "language_model.model.layers.20.feed_forward.experts.down_proj.SCB": "model-00012-of-00026.safetensors", "language_model.model.layers.20.feed_forward.experts.down_proj.weight": "model-00012-of-00026.safetensors", "language_model.model.layers.20.feed_forward.experts.down_proj.weight_format": "model-00012-of-00026.safetensors", - "language_model.model.layers.20.feed_forward.experts.gate_up_proj.SCB": "model-00011-of-00026.safetensors", - "language_model.model.layers.20.feed_forward.experts.gate_up_proj.weight": "model-00011-of-00026.safetensors", - "language_model.model.layers.20.feed_forward.experts.gate_up_proj.weight_format": "model-00011-of-00026.safetensors", - "language_model.model.layers.20.feed_forward.router.SCB": "model-00012-of-00026.safetensors", + "language_model.model.layers.20.feed_forward.experts.gate_proj.SCB": "model-00011-of-00026.safetensors", + "language_model.model.layers.20.feed_forward.experts.gate_proj.weight": "model-00011-of-00026.safetensors", + "language_model.model.layers.20.feed_forward.experts.gate_proj.weight_format": "model-00011-of-00026.safetensors", + "language_model.model.layers.20.feed_forward.experts.up_proj.SCB": "model-00012-of-00026.safetensors", + "language_model.model.layers.20.feed_forward.experts.up_proj.weight": "model-00012-of-00026.safetensors", + "language_model.model.layers.20.feed_forward.experts.up_proj.weight_format": "model-00012-of-00026.safetensors", "language_model.model.layers.20.feed_forward.router.weight": "model-00012-of-00026.safetensors", - "language_model.model.layers.20.feed_forward.router.weight_format": "model-00012-of-00026.safetensors", "language_model.model.layers.20.feed_forward.shared_expert.down_proj.SCB": "model-00012-of-00026.safetensors", "language_model.model.layers.20.feed_forward.shared_expert.down_proj.weight": "model-00012-of-00026.safetensors", "language_model.model.layers.20.feed_forward.shared_expert.down_proj.weight_format": "model-00012-of-00026.safetensors", @@ -456,12 +470,13 @@ "language_model.model.layers.21.feed_forward.experts.down_proj.SCB": "model-00012-of-00026.safetensors", "language_model.model.layers.21.feed_forward.experts.down_proj.weight": "model-00012-of-00026.safetensors", "language_model.model.layers.21.feed_forward.experts.down_proj.weight_format": "model-00012-of-00026.safetensors", - "language_model.model.layers.21.feed_forward.experts.gate_up_proj.SCB": "model-00012-of-00026.safetensors", - "language_model.model.layers.21.feed_forward.experts.gate_up_proj.weight": "model-00012-of-00026.safetensors", - "language_model.model.layers.21.feed_forward.experts.gate_up_proj.weight_format": "model-00012-of-00026.safetensors", - "language_model.model.layers.21.feed_forward.router.SCB": "model-00012-of-00026.safetensors", + "language_model.model.layers.21.feed_forward.experts.gate_proj.SCB": "model-00012-of-00026.safetensors", + "language_model.model.layers.21.feed_forward.experts.gate_proj.weight": "model-00012-of-00026.safetensors", + "language_model.model.layers.21.feed_forward.experts.gate_proj.weight_format": "model-00012-of-00026.safetensors", + "language_model.model.layers.21.feed_forward.experts.up_proj.SCB": "model-00012-of-00026.safetensors", + "language_model.model.layers.21.feed_forward.experts.up_proj.weight": "model-00012-of-00026.safetensors", + "language_model.model.layers.21.feed_forward.experts.up_proj.weight_format": "model-00012-of-00026.safetensors", "language_model.model.layers.21.feed_forward.router.weight": "model-00012-of-00026.safetensors", - "language_model.model.layers.21.feed_forward.router.weight_format": "model-00012-of-00026.safetensors", "language_model.model.layers.21.feed_forward.shared_expert.down_proj.SCB": "model-00012-of-00026.safetensors", "language_model.model.layers.21.feed_forward.shared_expert.down_proj.weight": "model-00012-of-00026.safetensors", "language_model.model.layers.21.feed_forward.shared_expert.down_proj.weight_format": "model-00012-of-00026.safetensors", @@ -488,12 +503,13 @@ "language_model.model.layers.22.feed_forward.experts.down_proj.SCB": "model-00013-of-00026.safetensors", "language_model.model.layers.22.feed_forward.experts.down_proj.weight": "model-00013-of-00026.safetensors", "language_model.model.layers.22.feed_forward.experts.down_proj.weight_format": "model-00013-of-00026.safetensors", - "language_model.model.layers.22.feed_forward.experts.gate_up_proj.SCB": "model-00012-of-00026.safetensors", - "language_model.model.layers.22.feed_forward.experts.gate_up_proj.weight": "model-00012-of-00026.safetensors", - "language_model.model.layers.22.feed_forward.experts.gate_up_proj.weight_format": "model-00012-of-00026.safetensors", - "language_model.model.layers.22.feed_forward.router.SCB": "model-00013-of-00026.safetensors", + "language_model.model.layers.22.feed_forward.experts.gate_proj.SCB": "model-00012-of-00026.safetensors", + "language_model.model.layers.22.feed_forward.experts.gate_proj.weight": "model-00012-of-00026.safetensors", + "language_model.model.layers.22.feed_forward.experts.gate_proj.weight_format": "model-00012-of-00026.safetensors", + "language_model.model.layers.22.feed_forward.experts.up_proj.SCB": "model-00013-of-00026.safetensors", + "language_model.model.layers.22.feed_forward.experts.up_proj.weight": "model-00013-of-00026.safetensors", + "language_model.model.layers.22.feed_forward.experts.up_proj.weight_format": "model-00013-of-00026.safetensors", "language_model.model.layers.22.feed_forward.router.weight": "model-00013-of-00026.safetensors", - "language_model.model.layers.22.feed_forward.router.weight_format": "model-00013-of-00026.safetensors", "language_model.model.layers.22.feed_forward.shared_expert.down_proj.SCB": "model-00013-of-00026.safetensors", "language_model.model.layers.22.feed_forward.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors", "language_model.model.layers.22.feed_forward.shared_expert.down_proj.weight_format": "model-00013-of-00026.safetensors", @@ -520,12 +536,13 @@ "language_model.model.layers.23.feed_forward.experts.down_proj.SCB": "model-00013-of-00026.safetensors", "language_model.model.layers.23.feed_forward.experts.down_proj.weight": "model-00013-of-00026.safetensors", "language_model.model.layers.23.feed_forward.experts.down_proj.weight_format": "model-00013-of-00026.safetensors", - "language_model.model.layers.23.feed_forward.experts.gate_up_proj.SCB": "model-00013-of-00026.safetensors", - "language_model.model.layers.23.feed_forward.experts.gate_up_proj.weight": "model-00013-of-00026.safetensors", - "language_model.model.layers.23.feed_forward.experts.gate_up_proj.weight_format": "model-00013-of-00026.safetensors", - "language_model.model.layers.23.feed_forward.router.SCB": "model-00013-of-00026.safetensors", + "language_model.model.layers.23.feed_forward.experts.gate_proj.SCB": "model-00013-of-00026.safetensors", + "language_model.model.layers.23.feed_forward.experts.gate_proj.weight": "model-00013-of-00026.safetensors", + "language_model.model.layers.23.feed_forward.experts.gate_proj.weight_format": "model-00013-of-00026.safetensors", + "language_model.model.layers.23.feed_forward.experts.up_proj.SCB": "model-00013-of-00026.safetensors", + "language_model.model.layers.23.feed_forward.experts.up_proj.weight": "model-00013-of-00026.safetensors", + "language_model.model.layers.23.feed_forward.experts.up_proj.weight_format": "model-00013-of-00026.safetensors", "language_model.model.layers.23.feed_forward.router.weight": "model-00013-of-00026.safetensors", - "language_model.model.layers.23.feed_forward.router.weight_format": "model-00013-of-00026.safetensors", "language_model.model.layers.23.feed_forward.shared_expert.down_proj.SCB": "model-00013-of-00026.safetensors", "language_model.model.layers.23.feed_forward.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors", "language_model.model.layers.23.feed_forward.shared_expert.down_proj.weight_format": "model-00013-of-00026.safetensors", @@ -552,12 +569,13 @@ "language_model.model.layers.24.feed_forward.experts.down_proj.SCB": "model-00014-of-00026.safetensors", "language_model.model.layers.24.feed_forward.experts.down_proj.weight": "model-00014-of-00026.safetensors", "language_model.model.layers.24.feed_forward.experts.down_proj.weight_format": "model-00014-of-00026.safetensors", - "language_model.model.layers.24.feed_forward.experts.gate_up_proj.SCB": "model-00013-of-00026.safetensors", - "language_model.model.layers.24.feed_forward.experts.gate_up_proj.weight": "model-00013-of-00026.safetensors", - "language_model.model.layers.24.feed_forward.experts.gate_up_proj.weight_format": "model-00013-of-00026.safetensors", - "language_model.model.layers.24.feed_forward.router.SCB": "model-00014-of-00026.safetensors", + "language_model.model.layers.24.feed_forward.experts.gate_proj.SCB": "model-00013-of-00026.safetensors", + "language_model.model.layers.24.feed_forward.experts.gate_proj.weight": "model-00013-of-00026.safetensors", + "language_model.model.layers.24.feed_forward.experts.gate_proj.weight_format": "model-00013-of-00026.safetensors", + "language_model.model.layers.24.feed_forward.experts.up_proj.SCB": "model-00014-of-00026.safetensors", + "language_model.model.layers.24.feed_forward.experts.up_proj.weight": "model-00014-of-00026.safetensors", + "language_model.model.layers.24.feed_forward.experts.up_proj.weight_format": "model-00014-of-00026.safetensors", "language_model.model.layers.24.feed_forward.router.weight": "model-00014-of-00026.safetensors", - "language_model.model.layers.24.feed_forward.router.weight_format": "model-00014-of-00026.safetensors", "language_model.model.layers.24.feed_forward.shared_expert.down_proj.SCB": "model-00014-of-00026.safetensors", "language_model.model.layers.24.feed_forward.shared_expert.down_proj.weight": "model-00014-of-00026.safetensors", "language_model.model.layers.24.feed_forward.shared_expert.down_proj.weight_format": "model-00014-of-00026.safetensors", @@ -584,12 +602,13 @@ "language_model.model.layers.25.feed_forward.experts.down_proj.SCB": "model-00014-of-00026.safetensors", "language_model.model.layers.25.feed_forward.experts.down_proj.weight": "model-00014-of-00026.safetensors", "language_model.model.layers.25.feed_forward.experts.down_proj.weight_format": "model-00014-of-00026.safetensors", - "language_model.model.layers.25.feed_forward.experts.gate_up_proj.SCB": "model-00014-of-00026.safetensors", - "language_model.model.layers.25.feed_forward.experts.gate_up_proj.weight": "model-00014-of-00026.safetensors", - "language_model.model.layers.25.feed_forward.experts.gate_up_proj.weight_format": "model-00014-of-00026.safetensors", - "language_model.model.layers.25.feed_forward.router.SCB": "model-00014-of-00026.safetensors", + "language_model.model.layers.25.feed_forward.experts.gate_proj.SCB": "model-00014-of-00026.safetensors", + "language_model.model.layers.25.feed_forward.experts.gate_proj.weight": "model-00014-of-00026.safetensors", + "language_model.model.layers.25.feed_forward.experts.gate_proj.weight_format": "model-00014-of-00026.safetensors", + "language_model.model.layers.25.feed_forward.experts.up_proj.SCB": "model-00014-of-00026.safetensors", + "language_model.model.layers.25.feed_forward.experts.up_proj.weight": "model-00014-of-00026.safetensors", + "language_model.model.layers.25.feed_forward.experts.up_proj.weight_format": "model-00014-of-00026.safetensors", "language_model.model.layers.25.feed_forward.router.weight": "model-00014-of-00026.safetensors", - "language_model.model.layers.25.feed_forward.router.weight_format": "model-00014-of-00026.safetensors", "language_model.model.layers.25.feed_forward.shared_expert.down_proj.SCB": "model-00014-of-00026.safetensors", "language_model.model.layers.25.feed_forward.shared_expert.down_proj.weight": "model-00014-of-00026.safetensors", "language_model.model.layers.25.feed_forward.shared_expert.down_proj.weight_format": "model-00014-of-00026.safetensors", @@ -616,12 +635,13 @@ "language_model.model.layers.26.feed_forward.experts.down_proj.SCB": "model-00015-of-00026.safetensors", "language_model.model.layers.26.feed_forward.experts.down_proj.weight": "model-00015-of-00026.safetensors", "language_model.model.layers.26.feed_forward.experts.down_proj.weight_format": "model-00015-of-00026.safetensors", - "language_model.model.layers.26.feed_forward.experts.gate_up_proj.SCB": "model-00014-of-00026.safetensors", - "language_model.model.layers.26.feed_forward.experts.gate_up_proj.weight": "model-00014-of-00026.safetensors", - "language_model.model.layers.26.feed_forward.experts.gate_up_proj.weight_format": "model-00014-of-00026.safetensors", - "language_model.model.layers.26.feed_forward.router.SCB": "model-00015-of-00026.safetensors", + "language_model.model.layers.26.feed_forward.experts.gate_proj.SCB": "model-00014-of-00026.safetensors", + "language_model.model.layers.26.feed_forward.experts.gate_proj.weight": "model-00014-of-00026.safetensors", + "language_model.model.layers.26.feed_forward.experts.gate_proj.weight_format": "model-00014-of-00026.safetensors", + "language_model.model.layers.26.feed_forward.experts.up_proj.SCB": "model-00015-of-00026.safetensors", + "language_model.model.layers.26.feed_forward.experts.up_proj.weight": "model-00015-of-00026.safetensors", + "language_model.model.layers.26.feed_forward.experts.up_proj.weight_format": "model-00015-of-00026.safetensors", "language_model.model.layers.26.feed_forward.router.weight": "model-00015-of-00026.safetensors", - "language_model.model.layers.26.feed_forward.router.weight_format": "model-00015-of-00026.safetensors", "language_model.model.layers.26.feed_forward.shared_expert.down_proj.SCB": "model-00015-of-00026.safetensors", "language_model.model.layers.26.feed_forward.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors", "language_model.model.layers.26.feed_forward.shared_expert.down_proj.weight_format": "model-00015-of-00026.safetensors", @@ -648,12 +668,13 @@ "language_model.model.layers.27.feed_forward.experts.down_proj.SCB": "model-00015-of-00026.safetensors", "language_model.model.layers.27.feed_forward.experts.down_proj.weight": "model-00015-of-00026.safetensors", "language_model.model.layers.27.feed_forward.experts.down_proj.weight_format": "model-00015-of-00026.safetensors", - "language_model.model.layers.27.feed_forward.experts.gate_up_proj.SCB": "model-00015-of-00026.safetensors", - "language_model.model.layers.27.feed_forward.experts.gate_up_proj.weight": "model-00015-of-00026.safetensors", - "language_model.model.layers.27.feed_forward.experts.gate_up_proj.weight_format": "model-00015-of-00026.safetensors", - "language_model.model.layers.27.feed_forward.router.SCB": "model-00015-of-00026.safetensors", + "language_model.model.layers.27.feed_forward.experts.gate_proj.SCB": "model-00015-of-00026.safetensors", + "language_model.model.layers.27.feed_forward.experts.gate_proj.weight": "model-00015-of-00026.safetensors", + "language_model.model.layers.27.feed_forward.experts.gate_proj.weight_format": "model-00015-of-00026.safetensors", + "language_model.model.layers.27.feed_forward.experts.up_proj.SCB": "model-00015-of-00026.safetensors", + "language_model.model.layers.27.feed_forward.experts.up_proj.weight": "model-00015-of-00026.safetensors", + "language_model.model.layers.27.feed_forward.experts.up_proj.weight_format": "model-00015-of-00026.safetensors", "language_model.model.layers.27.feed_forward.router.weight": "model-00015-of-00026.safetensors", - "language_model.model.layers.27.feed_forward.router.weight_format": "model-00015-of-00026.safetensors", "language_model.model.layers.27.feed_forward.shared_expert.down_proj.SCB": "model-00015-of-00026.safetensors", "language_model.model.layers.27.feed_forward.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors", "language_model.model.layers.27.feed_forward.shared_expert.down_proj.weight_format": "model-00015-of-00026.safetensors", @@ -680,12 +701,13 @@ "language_model.model.layers.28.feed_forward.experts.down_proj.SCB": "model-00016-of-00026.safetensors", "language_model.model.layers.28.feed_forward.experts.down_proj.weight": "model-00016-of-00026.safetensors", "language_model.model.layers.28.feed_forward.experts.down_proj.weight_format": "model-00016-of-00026.safetensors", - "language_model.model.layers.28.feed_forward.experts.gate_up_proj.SCB": "model-00015-of-00026.safetensors", - "language_model.model.layers.28.feed_forward.experts.gate_up_proj.weight": "model-00015-of-00026.safetensors", - "language_model.model.layers.28.feed_forward.experts.gate_up_proj.weight_format": "model-00015-of-00026.safetensors", - "language_model.model.layers.28.feed_forward.router.SCB": "model-00016-of-00026.safetensors", + "language_model.model.layers.28.feed_forward.experts.gate_proj.SCB": "model-00015-of-00026.safetensors", + "language_model.model.layers.28.feed_forward.experts.gate_proj.weight": "model-00015-of-00026.safetensors", + "language_model.model.layers.28.feed_forward.experts.gate_proj.weight_format": "model-00015-of-00026.safetensors", + "language_model.model.layers.28.feed_forward.experts.up_proj.SCB": "model-00016-of-00026.safetensors", + "language_model.model.layers.28.feed_forward.experts.up_proj.weight": "model-00016-of-00026.safetensors", + "language_model.model.layers.28.feed_forward.experts.up_proj.weight_format": "model-00016-of-00026.safetensors", "language_model.model.layers.28.feed_forward.router.weight": "model-00016-of-00026.safetensors", - "language_model.model.layers.28.feed_forward.router.weight_format": "model-00016-of-00026.safetensors", "language_model.model.layers.28.feed_forward.shared_expert.down_proj.SCB": "model-00016-of-00026.safetensors", "language_model.model.layers.28.feed_forward.shared_expert.down_proj.weight": "model-00016-of-00026.safetensors", "language_model.model.layers.28.feed_forward.shared_expert.down_proj.weight_format": "model-00016-of-00026.safetensors", @@ -712,12 +734,13 @@ "language_model.model.layers.29.feed_forward.experts.down_proj.SCB": "model-00016-of-00026.safetensors", "language_model.model.layers.29.feed_forward.experts.down_proj.weight": "model-00016-of-00026.safetensors", "language_model.model.layers.29.feed_forward.experts.down_proj.weight_format": "model-00016-of-00026.safetensors", - "language_model.model.layers.29.feed_forward.experts.gate_up_proj.SCB": "model-00016-of-00026.safetensors", - "language_model.model.layers.29.feed_forward.experts.gate_up_proj.weight": "model-00016-of-00026.safetensors", - "language_model.model.layers.29.feed_forward.experts.gate_up_proj.weight_format": "model-00016-of-00026.safetensors", - "language_model.model.layers.29.feed_forward.router.SCB": "model-00016-of-00026.safetensors", + "language_model.model.layers.29.feed_forward.experts.gate_proj.SCB": "model-00016-of-00026.safetensors", + "language_model.model.layers.29.feed_forward.experts.gate_proj.weight": "model-00016-of-00026.safetensors", + "language_model.model.layers.29.feed_forward.experts.gate_proj.weight_format": "model-00016-of-00026.safetensors", + "language_model.model.layers.29.feed_forward.experts.up_proj.SCB": "model-00016-of-00026.safetensors", + "language_model.model.layers.29.feed_forward.experts.up_proj.weight": "model-00016-of-00026.safetensors", + "language_model.model.layers.29.feed_forward.experts.up_proj.weight_format": "model-00016-of-00026.safetensors", "language_model.model.layers.29.feed_forward.router.weight": "model-00016-of-00026.safetensors", - "language_model.model.layers.29.feed_forward.router.weight_format": "model-00016-of-00026.safetensors", "language_model.model.layers.29.feed_forward.shared_expert.down_proj.SCB": "model-00016-of-00026.safetensors", "language_model.model.layers.29.feed_forward.shared_expert.down_proj.weight": "model-00016-of-00026.safetensors", "language_model.model.layers.29.feed_forward.shared_expert.down_proj.weight_format": "model-00016-of-00026.safetensors", @@ -744,12 +767,13 @@ "language_model.model.layers.3.feed_forward.experts.down_proj.SCB": "model-00003-of-00026.safetensors", "language_model.model.layers.3.feed_forward.experts.down_proj.weight": "model-00003-of-00026.safetensors", "language_model.model.layers.3.feed_forward.experts.down_proj.weight_format": "model-00003-of-00026.safetensors", - "language_model.model.layers.3.feed_forward.experts.gate_up_proj.SCB": "model-00003-of-00026.safetensors", - "language_model.model.layers.3.feed_forward.experts.gate_up_proj.weight": "model-00003-of-00026.safetensors", - "language_model.model.layers.3.feed_forward.experts.gate_up_proj.weight_format": "model-00003-of-00026.safetensors", - "language_model.model.layers.3.feed_forward.router.SCB": "model-00003-of-00026.safetensors", + "language_model.model.layers.3.feed_forward.experts.gate_proj.SCB": "model-00003-of-00026.safetensors", + "language_model.model.layers.3.feed_forward.experts.gate_proj.weight": "model-00003-of-00026.safetensors", + "language_model.model.layers.3.feed_forward.experts.gate_proj.weight_format": "model-00003-of-00026.safetensors", + "language_model.model.layers.3.feed_forward.experts.up_proj.SCB": "model-00003-of-00026.safetensors", + "language_model.model.layers.3.feed_forward.experts.up_proj.weight": "model-00003-of-00026.safetensors", + "language_model.model.layers.3.feed_forward.experts.up_proj.weight_format": "model-00003-of-00026.safetensors", "language_model.model.layers.3.feed_forward.router.weight": "model-00003-of-00026.safetensors", - "language_model.model.layers.3.feed_forward.router.weight_format": "model-00003-of-00026.safetensors", "language_model.model.layers.3.feed_forward.shared_expert.down_proj.SCB": "model-00003-of-00026.safetensors", "language_model.model.layers.3.feed_forward.shared_expert.down_proj.weight": "model-00003-of-00026.safetensors", "language_model.model.layers.3.feed_forward.shared_expert.down_proj.weight_format": "model-00003-of-00026.safetensors", @@ -776,12 +800,13 @@ "language_model.model.layers.30.feed_forward.experts.down_proj.SCB": "model-00017-of-00026.safetensors", "language_model.model.layers.30.feed_forward.experts.down_proj.weight": "model-00017-of-00026.safetensors", "language_model.model.layers.30.feed_forward.experts.down_proj.weight_format": "model-00017-of-00026.safetensors", - "language_model.model.layers.30.feed_forward.experts.gate_up_proj.SCB": "model-00016-of-00026.safetensors", - "language_model.model.layers.30.feed_forward.experts.gate_up_proj.weight": "model-00016-of-00026.safetensors", - "language_model.model.layers.30.feed_forward.experts.gate_up_proj.weight_format": "model-00016-of-00026.safetensors", - "language_model.model.layers.30.feed_forward.router.SCB": "model-00017-of-00026.safetensors", + "language_model.model.layers.30.feed_forward.experts.gate_proj.SCB": "model-00016-of-00026.safetensors", + "language_model.model.layers.30.feed_forward.experts.gate_proj.weight": "model-00016-of-00026.safetensors", + "language_model.model.layers.30.feed_forward.experts.gate_proj.weight_format": "model-00016-of-00026.safetensors", + "language_model.model.layers.30.feed_forward.experts.up_proj.SCB": "model-00017-of-00026.safetensors", + "language_model.model.layers.30.feed_forward.experts.up_proj.weight": "model-00017-of-00026.safetensors", + "language_model.model.layers.30.feed_forward.experts.up_proj.weight_format": "model-00017-of-00026.safetensors", "language_model.model.layers.30.feed_forward.router.weight": "model-00017-of-00026.safetensors", - "language_model.model.layers.30.feed_forward.router.weight_format": "model-00017-of-00026.safetensors", "language_model.model.layers.30.feed_forward.shared_expert.down_proj.SCB": "model-00017-of-00026.safetensors", "language_model.model.layers.30.feed_forward.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors", "language_model.model.layers.30.feed_forward.shared_expert.down_proj.weight_format": "model-00017-of-00026.safetensors", @@ -808,12 +833,13 @@ "language_model.model.layers.31.feed_forward.experts.down_proj.SCB": "model-00017-of-00026.safetensors", "language_model.model.layers.31.feed_forward.experts.down_proj.weight": "model-00017-of-00026.safetensors", "language_model.model.layers.31.feed_forward.experts.down_proj.weight_format": "model-00017-of-00026.safetensors", - "language_model.model.layers.31.feed_forward.experts.gate_up_proj.SCB": "model-00017-of-00026.safetensors", - "language_model.model.layers.31.feed_forward.experts.gate_up_proj.weight": "model-00017-of-00026.safetensors", - "language_model.model.layers.31.feed_forward.experts.gate_up_proj.weight_format": "model-00017-of-00026.safetensors", - "language_model.model.layers.31.feed_forward.router.SCB": "model-00017-of-00026.safetensors", + "language_model.model.layers.31.feed_forward.experts.gate_proj.SCB": "model-00017-of-00026.safetensors", + "language_model.model.layers.31.feed_forward.experts.gate_proj.weight": "model-00017-of-00026.safetensors", + "language_model.model.layers.31.feed_forward.experts.gate_proj.weight_format": "model-00017-of-00026.safetensors", + "language_model.model.layers.31.feed_forward.experts.up_proj.SCB": "model-00017-of-00026.safetensors", + "language_model.model.layers.31.feed_forward.experts.up_proj.weight": "model-00017-of-00026.safetensors", + "language_model.model.layers.31.feed_forward.experts.up_proj.weight_format": "model-00017-of-00026.safetensors", "language_model.model.layers.31.feed_forward.router.weight": "model-00017-of-00026.safetensors", - "language_model.model.layers.31.feed_forward.router.weight_format": "model-00017-of-00026.safetensors", "language_model.model.layers.31.feed_forward.shared_expert.down_proj.SCB": "model-00017-of-00026.safetensors", "language_model.model.layers.31.feed_forward.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors", "language_model.model.layers.31.feed_forward.shared_expert.down_proj.weight_format": "model-00017-of-00026.safetensors", @@ -840,12 +866,13 @@ "language_model.model.layers.32.feed_forward.experts.down_proj.SCB": "model-00018-of-00026.safetensors", "language_model.model.layers.32.feed_forward.experts.down_proj.weight": "model-00018-of-00026.safetensors", "language_model.model.layers.32.feed_forward.experts.down_proj.weight_format": "model-00018-of-00026.safetensors", - "language_model.model.layers.32.feed_forward.experts.gate_up_proj.SCB": "model-00017-of-00026.safetensors", - "language_model.model.layers.32.feed_forward.experts.gate_up_proj.weight": "model-00017-of-00026.safetensors", - "language_model.model.layers.32.feed_forward.experts.gate_up_proj.weight_format": "model-00017-of-00026.safetensors", - "language_model.model.layers.32.feed_forward.router.SCB": "model-00018-of-00026.safetensors", + "language_model.model.layers.32.feed_forward.experts.gate_proj.SCB": "model-00017-of-00026.safetensors", + "language_model.model.layers.32.feed_forward.experts.gate_proj.weight": "model-00017-of-00026.safetensors", + "language_model.model.layers.32.feed_forward.experts.gate_proj.weight_format": "model-00017-of-00026.safetensors", + "language_model.model.layers.32.feed_forward.experts.up_proj.SCB": "model-00018-of-00026.safetensors", + "language_model.model.layers.32.feed_forward.experts.up_proj.weight": "model-00018-of-00026.safetensors", + "language_model.model.layers.32.feed_forward.experts.up_proj.weight_format": "model-00018-of-00026.safetensors", "language_model.model.layers.32.feed_forward.router.weight": "model-00018-of-00026.safetensors", - "language_model.model.layers.32.feed_forward.router.weight_format": "model-00018-of-00026.safetensors", "language_model.model.layers.32.feed_forward.shared_expert.down_proj.SCB": "model-00018-of-00026.safetensors", "language_model.model.layers.32.feed_forward.shared_expert.down_proj.weight": "model-00018-of-00026.safetensors", "language_model.model.layers.32.feed_forward.shared_expert.down_proj.weight_format": "model-00018-of-00026.safetensors", @@ -872,12 +899,13 @@ "language_model.model.layers.33.feed_forward.experts.down_proj.SCB": "model-00018-of-00026.safetensors", "language_model.model.layers.33.feed_forward.experts.down_proj.weight": "model-00018-of-00026.safetensors", "language_model.model.layers.33.feed_forward.experts.down_proj.weight_format": "model-00018-of-00026.safetensors", - "language_model.model.layers.33.feed_forward.experts.gate_up_proj.SCB": "model-00018-of-00026.safetensors", - "language_model.model.layers.33.feed_forward.experts.gate_up_proj.weight": "model-00018-of-00026.safetensors", - "language_model.model.layers.33.feed_forward.experts.gate_up_proj.weight_format": "model-00018-of-00026.safetensors", - "language_model.model.layers.33.feed_forward.router.SCB": "model-00018-of-00026.safetensors", + "language_model.model.layers.33.feed_forward.experts.gate_proj.SCB": "model-00018-of-00026.safetensors", + "language_model.model.layers.33.feed_forward.experts.gate_proj.weight": "model-00018-of-00026.safetensors", + "language_model.model.layers.33.feed_forward.experts.gate_proj.weight_format": "model-00018-of-00026.safetensors", + "language_model.model.layers.33.feed_forward.experts.up_proj.SCB": "model-00018-of-00026.safetensors", + "language_model.model.layers.33.feed_forward.experts.up_proj.weight": "model-00018-of-00026.safetensors", + "language_model.model.layers.33.feed_forward.experts.up_proj.weight_format": "model-00018-of-00026.safetensors", "language_model.model.layers.33.feed_forward.router.weight": "model-00018-of-00026.safetensors", - "language_model.model.layers.33.feed_forward.router.weight_format": "model-00018-of-00026.safetensors", "language_model.model.layers.33.feed_forward.shared_expert.down_proj.SCB": "model-00018-of-00026.safetensors", "language_model.model.layers.33.feed_forward.shared_expert.down_proj.weight": "model-00018-of-00026.safetensors", "language_model.model.layers.33.feed_forward.shared_expert.down_proj.weight_format": "model-00018-of-00026.safetensors", @@ -904,12 +932,13 @@ "language_model.model.layers.34.feed_forward.experts.down_proj.SCB": "model-00019-of-00026.safetensors", "language_model.model.layers.34.feed_forward.experts.down_proj.weight": "model-00019-of-00026.safetensors", "language_model.model.layers.34.feed_forward.experts.down_proj.weight_format": "model-00019-of-00026.safetensors", - "language_model.model.layers.34.feed_forward.experts.gate_up_proj.SCB": "model-00018-of-00026.safetensors", - "language_model.model.layers.34.feed_forward.experts.gate_up_proj.weight": "model-00018-of-00026.safetensors", - "language_model.model.layers.34.feed_forward.experts.gate_up_proj.weight_format": "model-00018-of-00026.safetensors", - "language_model.model.layers.34.feed_forward.router.SCB": "model-00019-of-00026.safetensors", + "language_model.model.layers.34.feed_forward.experts.gate_proj.SCB": "model-00018-of-00026.safetensors", + "language_model.model.layers.34.feed_forward.experts.gate_proj.weight": "model-00018-of-00026.safetensors", + "language_model.model.layers.34.feed_forward.experts.gate_proj.weight_format": "model-00018-of-00026.safetensors", + "language_model.model.layers.34.feed_forward.experts.up_proj.SCB": "model-00019-of-00026.safetensors", + "language_model.model.layers.34.feed_forward.experts.up_proj.weight": "model-00019-of-00026.safetensors", + "language_model.model.layers.34.feed_forward.experts.up_proj.weight_format": "model-00019-of-00026.safetensors", "language_model.model.layers.34.feed_forward.router.weight": "model-00019-of-00026.safetensors", - "language_model.model.layers.34.feed_forward.router.weight_format": "model-00019-of-00026.safetensors", "language_model.model.layers.34.feed_forward.shared_expert.down_proj.SCB": "model-00019-of-00026.safetensors", "language_model.model.layers.34.feed_forward.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors", "language_model.model.layers.34.feed_forward.shared_expert.down_proj.weight_format": "model-00019-of-00026.safetensors", @@ -936,12 +965,13 @@ "language_model.model.layers.35.feed_forward.experts.down_proj.SCB": "model-00019-of-00026.safetensors", "language_model.model.layers.35.feed_forward.experts.down_proj.weight": "model-00019-of-00026.safetensors", "language_model.model.layers.35.feed_forward.experts.down_proj.weight_format": "model-00019-of-00026.safetensors", - "language_model.model.layers.35.feed_forward.experts.gate_up_proj.SCB": "model-00019-of-00026.safetensors", - "language_model.model.layers.35.feed_forward.experts.gate_up_proj.weight": "model-00019-of-00026.safetensors", - "language_model.model.layers.35.feed_forward.experts.gate_up_proj.weight_format": "model-00019-of-00026.safetensors", - "language_model.model.layers.35.feed_forward.router.SCB": "model-00019-of-00026.safetensors", + "language_model.model.layers.35.feed_forward.experts.gate_proj.SCB": "model-00019-of-00026.safetensors", + "language_model.model.layers.35.feed_forward.experts.gate_proj.weight": "model-00019-of-00026.safetensors", + "language_model.model.layers.35.feed_forward.experts.gate_proj.weight_format": "model-00019-of-00026.safetensors", + "language_model.model.layers.35.feed_forward.experts.up_proj.SCB": "model-00019-of-00026.safetensors", + "language_model.model.layers.35.feed_forward.experts.up_proj.weight": "model-00019-of-00026.safetensors", + "language_model.model.layers.35.feed_forward.experts.up_proj.weight_format": "model-00019-of-00026.safetensors", "language_model.model.layers.35.feed_forward.router.weight": "model-00019-of-00026.safetensors", - "language_model.model.layers.35.feed_forward.router.weight_format": "model-00019-of-00026.safetensors", "language_model.model.layers.35.feed_forward.shared_expert.down_proj.SCB": "model-00019-of-00026.safetensors", "language_model.model.layers.35.feed_forward.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors", "language_model.model.layers.35.feed_forward.shared_expert.down_proj.weight_format": "model-00019-of-00026.safetensors", @@ -968,12 +998,13 @@ "language_model.model.layers.36.feed_forward.experts.down_proj.SCB": "model-00020-of-00026.safetensors", "language_model.model.layers.36.feed_forward.experts.down_proj.weight": "model-00020-of-00026.safetensors", "language_model.model.layers.36.feed_forward.experts.down_proj.weight_format": "model-00020-of-00026.safetensors", - "language_model.model.layers.36.feed_forward.experts.gate_up_proj.SCB": "model-00019-of-00026.safetensors", - "language_model.model.layers.36.feed_forward.experts.gate_up_proj.weight": "model-00019-of-00026.safetensors", - "language_model.model.layers.36.feed_forward.experts.gate_up_proj.weight_format": "model-00019-of-00026.safetensors", - "language_model.model.layers.36.feed_forward.router.SCB": "model-00020-of-00026.safetensors", + "language_model.model.layers.36.feed_forward.experts.gate_proj.SCB": "model-00019-of-00026.safetensors", + "language_model.model.layers.36.feed_forward.experts.gate_proj.weight": "model-00019-of-00026.safetensors", + "language_model.model.layers.36.feed_forward.experts.gate_proj.weight_format": "model-00019-of-00026.safetensors", + "language_model.model.layers.36.feed_forward.experts.up_proj.SCB": "model-00020-of-00026.safetensors", + "language_model.model.layers.36.feed_forward.experts.up_proj.weight": "model-00020-of-00026.safetensors", + "language_model.model.layers.36.feed_forward.experts.up_proj.weight_format": "model-00020-of-00026.safetensors", "language_model.model.layers.36.feed_forward.router.weight": "model-00020-of-00026.safetensors", - "language_model.model.layers.36.feed_forward.router.weight_format": "model-00020-of-00026.safetensors", "language_model.model.layers.36.feed_forward.shared_expert.down_proj.SCB": "model-00020-of-00026.safetensors", "language_model.model.layers.36.feed_forward.shared_expert.down_proj.weight": "model-00020-of-00026.safetensors", "language_model.model.layers.36.feed_forward.shared_expert.down_proj.weight_format": "model-00020-of-00026.safetensors", @@ -1000,12 +1031,13 @@ "language_model.model.layers.37.feed_forward.experts.down_proj.SCB": "model-00020-of-00026.safetensors", "language_model.model.layers.37.feed_forward.experts.down_proj.weight": "model-00020-of-00026.safetensors", "language_model.model.layers.37.feed_forward.experts.down_proj.weight_format": "model-00020-of-00026.safetensors", - "language_model.model.layers.37.feed_forward.experts.gate_up_proj.SCB": "model-00020-of-00026.safetensors", - "language_model.model.layers.37.feed_forward.experts.gate_up_proj.weight": "model-00020-of-00026.safetensors", - "language_model.model.layers.37.feed_forward.experts.gate_up_proj.weight_format": "model-00020-of-00026.safetensors", - "language_model.model.layers.37.feed_forward.router.SCB": "model-00020-of-00026.safetensors", + "language_model.model.layers.37.feed_forward.experts.gate_proj.SCB": "model-00020-of-00026.safetensors", + "language_model.model.layers.37.feed_forward.experts.gate_proj.weight": "model-00020-of-00026.safetensors", + "language_model.model.layers.37.feed_forward.experts.gate_proj.weight_format": "model-00020-of-00026.safetensors", + "language_model.model.layers.37.feed_forward.experts.up_proj.SCB": "model-00020-of-00026.safetensors", + "language_model.model.layers.37.feed_forward.experts.up_proj.weight": "model-00020-of-00026.safetensors", + "language_model.model.layers.37.feed_forward.experts.up_proj.weight_format": "model-00020-of-00026.safetensors", "language_model.model.layers.37.feed_forward.router.weight": "model-00020-of-00026.safetensors", - "language_model.model.layers.37.feed_forward.router.weight_format": "model-00020-of-00026.safetensors", "language_model.model.layers.37.feed_forward.shared_expert.down_proj.SCB": "model-00020-of-00026.safetensors", "language_model.model.layers.37.feed_forward.shared_expert.down_proj.weight": "model-00020-of-00026.safetensors", "language_model.model.layers.37.feed_forward.shared_expert.down_proj.weight_format": "model-00020-of-00026.safetensors", @@ -1032,12 +1064,13 @@ "language_model.model.layers.38.feed_forward.experts.down_proj.SCB": "model-00021-of-00026.safetensors", "language_model.model.layers.38.feed_forward.experts.down_proj.weight": "model-00021-of-00026.safetensors", "language_model.model.layers.38.feed_forward.experts.down_proj.weight_format": "model-00021-of-00026.safetensors", - "language_model.model.layers.38.feed_forward.experts.gate_up_proj.SCB": "model-00020-of-00026.safetensors", - "language_model.model.layers.38.feed_forward.experts.gate_up_proj.weight": "model-00020-of-00026.safetensors", - "language_model.model.layers.38.feed_forward.experts.gate_up_proj.weight_format": "model-00020-of-00026.safetensors", - "language_model.model.layers.38.feed_forward.router.SCB": "model-00021-of-00026.safetensors", + "language_model.model.layers.38.feed_forward.experts.gate_proj.SCB": "model-00020-of-00026.safetensors", + "language_model.model.layers.38.feed_forward.experts.gate_proj.weight": "model-00020-of-00026.safetensors", + "language_model.model.layers.38.feed_forward.experts.gate_proj.weight_format": "model-00020-of-00026.safetensors", + "language_model.model.layers.38.feed_forward.experts.up_proj.SCB": "model-00021-of-00026.safetensors", + "language_model.model.layers.38.feed_forward.experts.up_proj.weight": "model-00021-of-00026.safetensors", + "language_model.model.layers.38.feed_forward.experts.up_proj.weight_format": "model-00021-of-00026.safetensors", "language_model.model.layers.38.feed_forward.router.weight": "model-00021-of-00026.safetensors", - "language_model.model.layers.38.feed_forward.router.weight_format": "model-00021-of-00026.safetensors", "language_model.model.layers.38.feed_forward.shared_expert.down_proj.SCB": "model-00021-of-00026.safetensors", "language_model.model.layers.38.feed_forward.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors", "language_model.model.layers.38.feed_forward.shared_expert.down_proj.weight_format": "model-00021-of-00026.safetensors", @@ -1064,12 +1097,13 @@ "language_model.model.layers.39.feed_forward.experts.down_proj.SCB": "model-00021-of-00026.safetensors", "language_model.model.layers.39.feed_forward.experts.down_proj.weight": "model-00021-of-00026.safetensors", "language_model.model.layers.39.feed_forward.experts.down_proj.weight_format": "model-00021-of-00026.safetensors", - "language_model.model.layers.39.feed_forward.experts.gate_up_proj.SCB": "model-00021-of-00026.safetensors", - "language_model.model.layers.39.feed_forward.experts.gate_up_proj.weight": "model-00021-of-00026.safetensors", - "language_model.model.layers.39.feed_forward.experts.gate_up_proj.weight_format": "model-00021-of-00026.safetensors", - "language_model.model.layers.39.feed_forward.router.SCB": "model-00021-of-00026.safetensors", + "language_model.model.layers.39.feed_forward.experts.gate_proj.SCB": "model-00021-of-00026.safetensors", + "language_model.model.layers.39.feed_forward.experts.gate_proj.weight": "model-00021-of-00026.safetensors", + "language_model.model.layers.39.feed_forward.experts.gate_proj.weight_format": "model-00021-of-00026.safetensors", + "language_model.model.layers.39.feed_forward.experts.up_proj.SCB": "model-00021-of-00026.safetensors", + "language_model.model.layers.39.feed_forward.experts.up_proj.weight": "model-00021-of-00026.safetensors", + "language_model.model.layers.39.feed_forward.experts.up_proj.weight_format": "model-00021-of-00026.safetensors", "language_model.model.layers.39.feed_forward.router.weight": "model-00021-of-00026.safetensors", - "language_model.model.layers.39.feed_forward.router.weight_format": "model-00021-of-00026.safetensors", "language_model.model.layers.39.feed_forward.shared_expert.down_proj.SCB": "model-00021-of-00026.safetensors", "language_model.model.layers.39.feed_forward.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors", "language_model.model.layers.39.feed_forward.shared_expert.down_proj.weight_format": "model-00021-of-00026.safetensors", @@ -1096,12 +1130,13 @@ "language_model.model.layers.4.feed_forward.experts.down_proj.SCB": "model-00004-of-00026.safetensors", "language_model.model.layers.4.feed_forward.experts.down_proj.weight": "model-00004-of-00026.safetensors", "language_model.model.layers.4.feed_forward.experts.down_proj.weight_format": "model-00004-of-00026.safetensors", - "language_model.model.layers.4.feed_forward.experts.gate_up_proj.SCB": "model-00003-of-00026.safetensors", - "language_model.model.layers.4.feed_forward.experts.gate_up_proj.weight": "model-00003-of-00026.safetensors", - "language_model.model.layers.4.feed_forward.experts.gate_up_proj.weight_format": "model-00003-of-00026.safetensors", - "language_model.model.layers.4.feed_forward.router.SCB": "model-00004-of-00026.safetensors", + "language_model.model.layers.4.feed_forward.experts.gate_proj.SCB": "model-00003-of-00026.safetensors", + "language_model.model.layers.4.feed_forward.experts.gate_proj.weight": "model-00003-of-00026.safetensors", + "language_model.model.layers.4.feed_forward.experts.gate_proj.weight_format": "model-00003-of-00026.safetensors", + "language_model.model.layers.4.feed_forward.experts.up_proj.SCB": "model-00004-of-00026.safetensors", + "language_model.model.layers.4.feed_forward.experts.up_proj.weight": "model-00004-of-00026.safetensors", + "language_model.model.layers.4.feed_forward.experts.up_proj.weight_format": "model-00004-of-00026.safetensors", "language_model.model.layers.4.feed_forward.router.weight": "model-00004-of-00026.safetensors", - "language_model.model.layers.4.feed_forward.router.weight_format": "model-00004-of-00026.safetensors", "language_model.model.layers.4.feed_forward.shared_expert.down_proj.SCB": "model-00004-of-00026.safetensors", "language_model.model.layers.4.feed_forward.shared_expert.down_proj.weight": "model-00004-of-00026.safetensors", "language_model.model.layers.4.feed_forward.shared_expert.down_proj.weight_format": "model-00004-of-00026.safetensors", @@ -1128,12 +1163,13 @@ "language_model.model.layers.40.feed_forward.experts.down_proj.SCB": "model-00022-of-00026.safetensors", "language_model.model.layers.40.feed_forward.experts.down_proj.weight": "model-00022-of-00026.safetensors", "language_model.model.layers.40.feed_forward.experts.down_proj.weight_format": "model-00022-of-00026.safetensors", - "language_model.model.layers.40.feed_forward.experts.gate_up_proj.SCB": "model-00021-of-00026.safetensors", - "language_model.model.layers.40.feed_forward.experts.gate_up_proj.weight": "model-00021-of-00026.safetensors", - "language_model.model.layers.40.feed_forward.experts.gate_up_proj.weight_format": "model-00021-of-00026.safetensors", - "language_model.model.layers.40.feed_forward.router.SCB": "model-00022-of-00026.safetensors", + "language_model.model.layers.40.feed_forward.experts.gate_proj.SCB": "model-00021-of-00026.safetensors", + "language_model.model.layers.40.feed_forward.experts.gate_proj.weight": "model-00021-of-00026.safetensors", + "language_model.model.layers.40.feed_forward.experts.gate_proj.weight_format": "model-00021-of-00026.safetensors", + "language_model.model.layers.40.feed_forward.experts.up_proj.SCB": "model-00022-of-00026.safetensors", + "language_model.model.layers.40.feed_forward.experts.up_proj.weight": "model-00022-of-00026.safetensors", + "language_model.model.layers.40.feed_forward.experts.up_proj.weight_format": "model-00022-of-00026.safetensors", "language_model.model.layers.40.feed_forward.router.weight": "model-00022-of-00026.safetensors", - "language_model.model.layers.40.feed_forward.router.weight_format": "model-00022-of-00026.safetensors", "language_model.model.layers.40.feed_forward.shared_expert.down_proj.SCB": "model-00022-of-00026.safetensors", "language_model.model.layers.40.feed_forward.shared_expert.down_proj.weight": "model-00022-of-00026.safetensors", "language_model.model.layers.40.feed_forward.shared_expert.down_proj.weight_format": "model-00022-of-00026.safetensors", @@ -1160,12 +1196,13 @@ "language_model.model.layers.41.feed_forward.experts.down_proj.SCB": "model-00022-of-00026.safetensors", "language_model.model.layers.41.feed_forward.experts.down_proj.weight": "model-00022-of-00026.safetensors", "language_model.model.layers.41.feed_forward.experts.down_proj.weight_format": "model-00022-of-00026.safetensors", - "language_model.model.layers.41.feed_forward.experts.gate_up_proj.SCB": "model-00022-of-00026.safetensors", - "language_model.model.layers.41.feed_forward.experts.gate_up_proj.weight": "model-00022-of-00026.safetensors", - "language_model.model.layers.41.feed_forward.experts.gate_up_proj.weight_format": "model-00022-of-00026.safetensors", - "language_model.model.layers.41.feed_forward.router.SCB": "model-00022-of-00026.safetensors", + "language_model.model.layers.41.feed_forward.experts.gate_proj.SCB": "model-00022-of-00026.safetensors", + "language_model.model.layers.41.feed_forward.experts.gate_proj.weight": "model-00022-of-00026.safetensors", + "language_model.model.layers.41.feed_forward.experts.gate_proj.weight_format": "model-00022-of-00026.safetensors", + "language_model.model.layers.41.feed_forward.experts.up_proj.SCB": "model-00022-of-00026.safetensors", + "language_model.model.layers.41.feed_forward.experts.up_proj.weight": "model-00022-of-00026.safetensors", + "language_model.model.layers.41.feed_forward.experts.up_proj.weight_format": "model-00022-of-00026.safetensors", "language_model.model.layers.41.feed_forward.router.weight": "model-00022-of-00026.safetensors", - "language_model.model.layers.41.feed_forward.router.weight_format": "model-00022-of-00026.safetensors", "language_model.model.layers.41.feed_forward.shared_expert.down_proj.SCB": "model-00022-of-00026.safetensors", "language_model.model.layers.41.feed_forward.shared_expert.down_proj.weight": "model-00022-of-00026.safetensors", "language_model.model.layers.41.feed_forward.shared_expert.down_proj.weight_format": "model-00022-of-00026.safetensors", @@ -1192,12 +1229,13 @@ "language_model.model.layers.42.feed_forward.experts.down_proj.SCB": "model-00023-of-00026.safetensors", "language_model.model.layers.42.feed_forward.experts.down_proj.weight": "model-00023-of-00026.safetensors", "language_model.model.layers.42.feed_forward.experts.down_proj.weight_format": "model-00023-of-00026.safetensors", - "language_model.model.layers.42.feed_forward.experts.gate_up_proj.SCB": "model-00022-of-00026.safetensors", - "language_model.model.layers.42.feed_forward.experts.gate_up_proj.weight": "model-00022-of-00026.safetensors", - "language_model.model.layers.42.feed_forward.experts.gate_up_proj.weight_format": "model-00022-of-00026.safetensors", - "language_model.model.layers.42.feed_forward.router.SCB": "model-00023-of-00026.safetensors", + "language_model.model.layers.42.feed_forward.experts.gate_proj.SCB": "model-00022-of-00026.safetensors", + "language_model.model.layers.42.feed_forward.experts.gate_proj.weight": "model-00022-of-00026.safetensors", + "language_model.model.layers.42.feed_forward.experts.gate_proj.weight_format": "model-00022-of-00026.safetensors", + "language_model.model.layers.42.feed_forward.experts.up_proj.SCB": "model-00023-of-00026.safetensors", + "language_model.model.layers.42.feed_forward.experts.up_proj.weight": "model-00023-of-00026.safetensors", + "language_model.model.layers.42.feed_forward.experts.up_proj.weight_format": "model-00023-of-00026.safetensors", "language_model.model.layers.42.feed_forward.router.weight": "model-00023-of-00026.safetensors", - "language_model.model.layers.42.feed_forward.router.weight_format": "model-00023-of-00026.safetensors", "language_model.model.layers.42.feed_forward.shared_expert.down_proj.SCB": "model-00023-of-00026.safetensors", "language_model.model.layers.42.feed_forward.shared_expert.down_proj.weight": "model-00023-of-00026.safetensors", "language_model.model.layers.42.feed_forward.shared_expert.down_proj.weight_format": "model-00023-of-00026.safetensors", @@ -1224,12 +1262,13 @@ "language_model.model.layers.43.feed_forward.experts.down_proj.SCB": "model-00023-of-00026.safetensors", "language_model.model.layers.43.feed_forward.experts.down_proj.weight": "model-00023-of-00026.safetensors", "language_model.model.layers.43.feed_forward.experts.down_proj.weight_format": "model-00023-of-00026.safetensors", - "language_model.model.layers.43.feed_forward.experts.gate_up_proj.SCB": "model-00023-of-00026.safetensors", - "language_model.model.layers.43.feed_forward.experts.gate_up_proj.weight": "model-00023-of-00026.safetensors", - "language_model.model.layers.43.feed_forward.experts.gate_up_proj.weight_format": "model-00023-of-00026.safetensors", - "language_model.model.layers.43.feed_forward.router.SCB": "model-00023-of-00026.safetensors", + "language_model.model.layers.43.feed_forward.experts.gate_proj.SCB": "model-00023-of-00026.safetensors", + "language_model.model.layers.43.feed_forward.experts.gate_proj.weight": "model-00023-of-00026.safetensors", + "language_model.model.layers.43.feed_forward.experts.gate_proj.weight_format": "model-00023-of-00026.safetensors", + "language_model.model.layers.43.feed_forward.experts.up_proj.SCB": "model-00023-of-00026.safetensors", + "language_model.model.layers.43.feed_forward.experts.up_proj.weight": "model-00023-of-00026.safetensors", + "language_model.model.layers.43.feed_forward.experts.up_proj.weight_format": "model-00023-of-00026.safetensors", "language_model.model.layers.43.feed_forward.router.weight": "model-00023-of-00026.safetensors", - "language_model.model.layers.43.feed_forward.router.weight_format": "model-00023-of-00026.safetensors", "language_model.model.layers.43.feed_forward.shared_expert.down_proj.SCB": "model-00023-of-00026.safetensors", "language_model.model.layers.43.feed_forward.shared_expert.down_proj.weight": "model-00023-of-00026.safetensors", "language_model.model.layers.43.feed_forward.shared_expert.down_proj.weight_format": "model-00023-of-00026.safetensors", @@ -1256,12 +1295,13 @@ "language_model.model.layers.44.feed_forward.experts.down_proj.SCB": "model-00024-of-00026.safetensors", "language_model.model.layers.44.feed_forward.experts.down_proj.weight": "model-00024-of-00026.safetensors", "language_model.model.layers.44.feed_forward.experts.down_proj.weight_format": "model-00024-of-00026.safetensors", - "language_model.model.layers.44.feed_forward.experts.gate_up_proj.SCB": "model-00023-of-00026.safetensors", - "language_model.model.layers.44.feed_forward.experts.gate_up_proj.weight": "model-00023-of-00026.safetensors", - "language_model.model.layers.44.feed_forward.experts.gate_up_proj.weight_format": "model-00023-of-00026.safetensors", - "language_model.model.layers.44.feed_forward.router.SCB": "model-00024-of-00026.safetensors", + "language_model.model.layers.44.feed_forward.experts.gate_proj.SCB": "model-00023-of-00026.safetensors", + "language_model.model.layers.44.feed_forward.experts.gate_proj.weight": "model-00023-of-00026.safetensors", + "language_model.model.layers.44.feed_forward.experts.gate_proj.weight_format": "model-00023-of-00026.safetensors", + "language_model.model.layers.44.feed_forward.experts.up_proj.SCB": "model-00024-of-00026.safetensors", + "language_model.model.layers.44.feed_forward.experts.up_proj.weight": "model-00024-of-00026.safetensors", + "language_model.model.layers.44.feed_forward.experts.up_proj.weight_format": "model-00024-of-00026.safetensors", "language_model.model.layers.44.feed_forward.router.weight": "model-00024-of-00026.safetensors", - "language_model.model.layers.44.feed_forward.router.weight_format": "model-00024-of-00026.safetensors", "language_model.model.layers.44.feed_forward.shared_expert.down_proj.SCB": "model-00024-of-00026.safetensors", "language_model.model.layers.44.feed_forward.shared_expert.down_proj.weight": "model-00024-of-00026.safetensors", "language_model.model.layers.44.feed_forward.shared_expert.down_proj.weight_format": "model-00024-of-00026.safetensors", @@ -1288,12 +1328,13 @@ "language_model.model.layers.45.feed_forward.experts.down_proj.SCB": "model-00024-of-00026.safetensors", "language_model.model.layers.45.feed_forward.experts.down_proj.weight": "model-00024-of-00026.safetensors", "language_model.model.layers.45.feed_forward.experts.down_proj.weight_format": "model-00024-of-00026.safetensors", - "language_model.model.layers.45.feed_forward.experts.gate_up_proj.SCB": "model-00024-of-00026.safetensors", - "language_model.model.layers.45.feed_forward.experts.gate_up_proj.weight": "model-00024-of-00026.safetensors", - "language_model.model.layers.45.feed_forward.experts.gate_up_proj.weight_format": "model-00024-of-00026.safetensors", - "language_model.model.layers.45.feed_forward.router.SCB": "model-00024-of-00026.safetensors", + "language_model.model.layers.45.feed_forward.experts.gate_proj.SCB": "model-00024-of-00026.safetensors", + "language_model.model.layers.45.feed_forward.experts.gate_proj.weight": "model-00024-of-00026.safetensors", + "language_model.model.layers.45.feed_forward.experts.gate_proj.weight_format": "model-00024-of-00026.safetensors", + "language_model.model.layers.45.feed_forward.experts.up_proj.SCB": "model-00024-of-00026.safetensors", + "language_model.model.layers.45.feed_forward.experts.up_proj.weight": "model-00024-of-00026.safetensors", + "language_model.model.layers.45.feed_forward.experts.up_proj.weight_format": "model-00024-of-00026.safetensors", "language_model.model.layers.45.feed_forward.router.weight": "model-00024-of-00026.safetensors", - "language_model.model.layers.45.feed_forward.router.weight_format": "model-00024-of-00026.safetensors", "language_model.model.layers.45.feed_forward.shared_expert.down_proj.SCB": "model-00024-of-00026.safetensors", "language_model.model.layers.45.feed_forward.shared_expert.down_proj.weight": "model-00024-of-00026.safetensors", "language_model.model.layers.45.feed_forward.shared_expert.down_proj.weight_format": "model-00024-of-00026.safetensors", @@ -1320,12 +1361,13 @@ "language_model.model.layers.46.feed_forward.experts.down_proj.SCB": "model-00025-of-00026.safetensors", "language_model.model.layers.46.feed_forward.experts.down_proj.weight": "model-00025-of-00026.safetensors", "language_model.model.layers.46.feed_forward.experts.down_proj.weight_format": "model-00025-of-00026.safetensors", - "language_model.model.layers.46.feed_forward.experts.gate_up_proj.SCB": "model-00024-of-00026.safetensors", - "language_model.model.layers.46.feed_forward.experts.gate_up_proj.weight": "model-00024-of-00026.safetensors", - "language_model.model.layers.46.feed_forward.experts.gate_up_proj.weight_format": "model-00024-of-00026.safetensors", - "language_model.model.layers.46.feed_forward.router.SCB": "model-00025-of-00026.safetensors", + "language_model.model.layers.46.feed_forward.experts.gate_proj.SCB": "model-00024-of-00026.safetensors", + "language_model.model.layers.46.feed_forward.experts.gate_proj.weight": "model-00024-of-00026.safetensors", + "language_model.model.layers.46.feed_forward.experts.gate_proj.weight_format": "model-00024-of-00026.safetensors", + "language_model.model.layers.46.feed_forward.experts.up_proj.SCB": "model-00025-of-00026.safetensors", + "language_model.model.layers.46.feed_forward.experts.up_proj.weight": "model-00025-of-00026.safetensors", + "language_model.model.layers.46.feed_forward.experts.up_proj.weight_format": "model-00025-of-00026.safetensors", "language_model.model.layers.46.feed_forward.router.weight": "model-00025-of-00026.safetensors", - "language_model.model.layers.46.feed_forward.router.weight_format": "model-00025-of-00026.safetensors", "language_model.model.layers.46.feed_forward.shared_expert.down_proj.SCB": "model-00025-of-00026.safetensors", "language_model.model.layers.46.feed_forward.shared_expert.down_proj.weight": "model-00025-of-00026.safetensors", "language_model.model.layers.46.feed_forward.shared_expert.down_proj.weight_format": "model-00025-of-00026.safetensors", @@ -1352,12 +1394,13 @@ "language_model.model.layers.47.feed_forward.experts.down_proj.SCB": "model-00025-of-00026.safetensors", "language_model.model.layers.47.feed_forward.experts.down_proj.weight": "model-00025-of-00026.safetensors", "language_model.model.layers.47.feed_forward.experts.down_proj.weight_format": "model-00025-of-00026.safetensors", - "language_model.model.layers.47.feed_forward.experts.gate_up_proj.SCB": "model-00025-of-00026.safetensors", - "language_model.model.layers.47.feed_forward.experts.gate_up_proj.weight": "model-00025-of-00026.safetensors", - "language_model.model.layers.47.feed_forward.experts.gate_up_proj.weight_format": "model-00025-of-00026.safetensors", - "language_model.model.layers.47.feed_forward.router.SCB": "model-00025-of-00026.safetensors", + "language_model.model.layers.47.feed_forward.experts.gate_proj.SCB": "model-00025-of-00026.safetensors", + "language_model.model.layers.47.feed_forward.experts.gate_proj.weight": "model-00025-of-00026.safetensors", + "language_model.model.layers.47.feed_forward.experts.gate_proj.weight_format": "model-00025-of-00026.safetensors", + "language_model.model.layers.47.feed_forward.experts.up_proj.SCB": "model-00025-of-00026.safetensors", + "language_model.model.layers.47.feed_forward.experts.up_proj.weight": "model-00025-of-00026.safetensors", + "language_model.model.layers.47.feed_forward.experts.up_proj.weight_format": "model-00025-of-00026.safetensors", "language_model.model.layers.47.feed_forward.router.weight": "model-00025-of-00026.safetensors", - "language_model.model.layers.47.feed_forward.router.weight_format": "model-00025-of-00026.safetensors", "language_model.model.layers.47.feed_forward.shared_expert.down_proj.SCB": "model-00025-of-00026.safetensors", "language_model.model.layers.47.feed_forward.shared_expert.down_proj.weight": "model-00025-of-00026.safetensors", "language_model.model.layers.47.feed_forward.shared_expert.down_proj.weight_format": "model-00025-of-00026.safetensors", @@ -1384,12 +1427,13 @@ "language_model.model.layers.5.feed_forward.experts.down_proj.SCB": "model-00004-of-00026.safetensors", "language_model.model.layers.5.feed_forward.experts.down_proj.weight": "model-00004-of-00026.safetensors", "language_model.model.layers.5.feed_forward.experts.down_proj.weight_format": "model-00004-of-00026.safetensors", - "language_model.model.layers.5.feed_forward.experts.gate_up_proj.SCB": "model-00004-of-00026.safetensors", - "language_model.model.layers.5.feed_forward.experts.gate_up_proj.weight": "model-00004-of-00026.safetensors", - "language_model.model.layers.5.feed_forward.experts.gate_up_proj.weight_format": "model-00004-of-00026.safetensors", - "language_model.model.layers.5.feed_forward.router.SCB": "model-00004-of-00026.safetensors", + "language_model.model.layers.5.feed_forward.experts.gate_proj.SCB": "model-00004-of-00026.safetensors", + "language_model.model.layers.5.feed_forward.experts.gate_proj.weight": "model-00004-of-00026.safetensors", + "language_model.model.layers.5.feed_forward.experts.gate_proj.weight_format": "model-00004-of-00026.safetensors", + "language_model.model.layers.5.feed_forward.experts.up_proj.SCB": "model-00004-of-00026.safetensors", + "language_model.model.layers.5.feed_forward.experts.up_proj.weight": "model-00004-of-00026.safetensors", + "language_model.model.layers.5.feed_forward.experts.up_proj.weight_format": "model-00004-of-00026.safetensors", "language_model.model.layers.5.feed_forward.router.weight": "model-00004-of-00026.safetensors", - "language_model.model.layers.5.feed_forward.router.weight_format": "model-00004-of-00026.safetensors", "language_model.model.layers.5.feed_forward.shared_expert.down_proj.SCB": "model-00004-of-00026.safetensors", "language_model.model.layers.5.feed_forward.shared_expert.down_proj.weight": "model-00004-of-00026.safetensors", "language_model.model.layers.5.feed_forward.shared_expert.down_proj.weight_format": "model-00004-of-00026.safetensors", @@ -1416,12 +1460,13 @@ "language_model.model.layers.6.feed_forward.experts.down_proj.SCB": "model-00005-of-00026.safetensors", "language_model.model.layers.6.feed_forward.experts.down_proj.weight": "model-00005-of-00026.safetensors", "language_model.model.layers.6.feed_forward.experts.down_proj.weight_format": "model-00005-of-00026.safetensors", - "language_model.model.layers.6.feed_forward.experts.gate_up_proj.SCB": "model-00004-of-00026.safetensors", - "language_model.model.layers.6.feed_forward.experts.gate_up_proj.weight": "model-00004-of-00026.safetensors", - "language_model.model.layers.6.feed_forward.experts.gate_up_proj.weight_format": "model-00004-of-00026.safetensors", - "language_model.model.layers.6.feed_forward.router.SCB": "model-00005-of-00026.safetensors", + "language_model.model.layers.6.feed_forward.experts.gate_proj.SCB": "model-00004-of-00026.safetensors", + "language_model.model.layers.6.feed_forward.experts.gate_proj.weight": "model-00004-of-00026.safetensors", + "language_model.model.layers.6.feed_forward.experts.gate_proj.weight_format": "model-00004-of-00026.safetensors", + "language_model.model.layers.6.feed_forward.experts.up_proj.SCB": "model-00005-of-00026.safetensors", + "language_model.model.layers.6.feed_forward.experts.up_proj.weight": "model-00005-of-00026.safetensors", + "language_model.model.layers.6.feed_forward.experts.up_proj.weight_format": "model-00005-of-00026.safetensors", "language_model.model.layers.6.feed_forward.router.weight": "model-00005-of-00026.safetensors", - "language_model.model.layers.6.feed_forward.router.weight_format": "model-00005-of-00026.safetensors", "language_model.model.layers.6.feed_forward.shared_expert.down_proj.SCB": "model-00005-of-00026.safetensors", "language_model.model.layers.6.feed_forward.shared_expert.down_proj.weight": "model-00005-of-00026.safetensors", "language_model.model.layers.6.feed_forward.shared_expert.down_proj.weight_format": "model-00005-of-00026.safetensors", @@ -1448,12 +1493,13 @@ "language_model.model.layers.7.feed_forward.experts.down_proj.SCB": "model-00005-of-00026.safetensors", "language_model.model.layers.7.feed_forward.experts.down_proj.weight": "model-00005-of-00026.safetensors", "language_model.model.layers.7.feed_forward.experts.down_proj.weight_format": "model-00005-of-00026.safetensors", - "language_model.model.layers.7.feed_forward.experts.gate_up_proj.SCB": "model-00005-of-00026.safetensors", - "language_model.model.layers.7.feed_forward.experts.gate_up_proj.weight": "model-00005-of-00026.safetensors", - "language_model.model.layers.7.feed_forward.experts.gate_up_proj.weight_format": "model-00005-of-00026.safetensors", - "language_model.model.layers.7.feed_forward.router.SCB": "model-00005-of-00026.safetensors", + "language_model.model.layers.7.feed_forward.experts.gate_proj.SCB": "model-00005-of-00026.safetensors", + "language_model.model.layers.7.feed_forward.experts.gate_proj.weight": "model-00005-of-00026.safetensors", + "language_model.model.layers.7.feed_forward.experts.gate_proj.weight_format": "model-00005-of-00026.safetensors", + "language_model.model.layers.7.feed_forward.experts.up_proj.SCB": "model-00005-of-00026.safetensors", + "language_model.model.layers.7.feed_forward.experts.up_proj.weight": "model-00005-of-00026.safetensors", + "language_model.model.layers.7.feed_forward.experts.up_proj.weight_format": "model-00005-of-00026.safetensors", "language_model.model.layers.7.feed_forward.router.weight": "model-00005-of-00026.safetensors", - "language_model.model.layers.7.feed_forward.router.weight_format": "model-00005-of-00026.safetensors", "language_model.model.layers.7.feed_forward.shared_expert.down_proj.SCB": "model-00005-of-00026.safetensors", "language_model.model.layers.7.feed_forward.shared_expert.down_proj.weight": "model-00005-of-00026.safetensors", "language_model.model.layers.7.feed_forward.shared_expert.down_proj.weight_format": "model-00005-of-00026.safetensors", @@ -1480,12 +1526,13 @@ "language_model.model.layers.8.feed_forward.experts.down_proj.SCB": "model-00006-of-00026.safetensors", "language_model.model.layers.8.feed_forward.experts.down_proj.weight": "model-00006-of-00026.safetensors", "language_model.model.layers.8.feed_forward.experts.down_proj.weight_format": "model-00006-of-00026.safetensors", - "language_model.model.layers.8.feed_forward.experts.gate_up_proj.SCB": "model-00005-of-00026.safetensors", - "language_model.model.layers.8.feed_forward.experts.gate_up_proj.weight": "model-00005-of-00026.safetensors", - "language_model.model.layers.8.feed_forward.experts.gate_up_proj.weight_format": "model-00005-of-00026.safetensors", - "language_model.model.layers.8.feed_forward.router.SCB": "model-00006-of-00026.safetensors", + "language_model.model.layers.8.feed_forward.experts.gate_proj.SCB": "model-00005-of-00026.safetensors", + "language_model.model.layers.8.feed_forward.experts.gate_proj.weight": "model-00005-of-00026.safetensors", + "language_model.model.layers.8.feed_forward.experts.gate_proj.weight_format": "model-00005-of-00026.safetensors", + "language_model.model.layers.8.feed_forward.experts.up_proj.SCB": "model-00006-of-00026.safetensors", + "language_model.model.layers.8.feed_forward.experts.up_proj.weight": "model-00006-of-00026.safetensors", + "language_model.model.layers.8.feed_forward.experts.up_proj.weight_format": "model-00006-of-00026.safetensors", "language_model.model.layers.8.feed_forward.router.weight": "model-00006-of-00026.safetensors", - "language_model.model.layers.8.feed_forward.router.weight_format": "model-00006-of-00026.safetensors", "language_model.model.layers.8.feed_forward.shared_expert.down_proj.SCB": "model-00006-of-00026.safetensors", "language_model.model.layers.8.feed_forward.shared_expert.down_proj.weight": "model-00006-of-00026.safetensors", "language_model.model.layers.8.feed_forward.shared_expert.down_proj.weight_format": "model-00006-of-00026.safetensors", @@ -1512,12 +1559,13 @@ "language_model.model.layers.9.feed_forward.experts.down_proj.SCB": "model-00006-of-00026.safetensors", "language_model.model.layers.9.feed_forward.experts.down_proj.weight": "model-00006-of-00026.safetensors", "language_model.model.layers.9.feed_forward.experts.down_proj.weight_format": "model-00006-of-00026.safetensors", - "language_model.model.layers.9.feed_forward.experts.gate_up_proj.SCB": "model-00006-of-00026.safetensors", - "language_model.model.layers.9.feed_forward.experts.gate_up_proj.weight": "model-00006-of-00026.safetensors", - "language_model.model.layers.9.feed_forward.experts.gate_up_proj.weight_format": "model-00006-of-00026.safetensors", - "language_model.model.layers.9.feed_forward.router.SCB": "model-00006-of-00026.safetensors", + "language_model.model.layers.9.feed_forward.experts.gate_proj.SCB": "model-00006-of-00026.safetensors", + "language_model.model.layers.9.feed_forward.experts.gate_proj.weight": "model-00006-of-00026.safetensors", + "language_model.model.layers.9.feed_forward.experts.gate_proj.weight_format": "model-00006-of-00026.safetensors", + "language_model.model.layers.9.feed_forward.experts.up_proj.SCB": "model-00006-of-00026.safetensors", + "language_model.model.layers.9.feed_forward.experts.up_proj.weight": "model-00006-of-00026.safetensors", + "language_model.model.layers.9.feed_forward.experts.up_proj.weight_format": "model-00006-of-00026.safetensors", "language_model.model.layers.9.feed_forward.router.weight": "model-00006-of-00026.safetensors", - "language_model.model.layers.9.feed_forward.router.weight_format": "model-00006-of-00026.safetensors", "language_model.model.layers.9.feed_forward.shared_expert.down_proj.SCB": "model-00006-of-00026.safetensors", "language_model.model.layers.9.feed_forward.shared_expert.down_proj.weight": "model-00006-of-00026.safetensors", "language_model.model.layers.9.feed_forward.shared_expert.down_proj.weight_format": "model-00006-of-00026.safetensors", @@ -1542,9 +1590,7 @@ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", "language_model.model.layers.9.self_attn.v_proj.weight_format": "model-00006-of-00026.safetensors", "language_model.model.norm.weight": "model-00025-of-00026.safetensors", - "multi_modal_projector.linear_1.SCB": "model-00001-of-00026.safetensors", "multi_modal_projector.linear_1.weight": "model-00001-of-00026.safetensors", - "multi_modal_projector.linear_1.weight_format": "model-00001-of-00026.safetensors", "vision_model.class_embedding": "model-00001-of-00026.safetensors", "vision_model.layernorm_post.bias": "model-00001-of-00026.safetensors", "vision_model.layernorm_post.weight": "model-00001-of-00026.safetensors", @@ -1552,965 +1598,551 @@ "vision_model.layernorm_pre.weight": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.0.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.1.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.10.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.11.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.12.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.13.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.14.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.15.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.16.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.17.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.18.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.19.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.2.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.20.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.21.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.22.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.23.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.24.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.25.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.26.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.27.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.28.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.28.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.29.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.29.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.3.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.30.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.30.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.31.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.31.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.32.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.32.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.33.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.33.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.4.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.5.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.6.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.7.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.8.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.input_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.input_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.mlp.fc1.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.mlp.fc2.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.mlp.fc2.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.mlp.fc2.weight_format": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.post_attention_layernorm.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.self_attn.k_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.self_attn.k_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.self_attn.o_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.self_attn.o_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.self_attn.o_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.self_attn.q_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.self_attn.q_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.self_attn.v_proj.SCB": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", "vision_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", - "vision_model.model.layers.9.self_attn.v_proj.weight_format": "model-00001-of-00026.safetensors", - "vision_model.patch_embedding.linear.SCB": "model-00001-of-00026.safetensors", "vision_model.patch_embedding.linear.weight": "model-00001-of-00026.safetensors", - "vision_model.patch_embedding.linear.weight_format": "model-00001-of-00026.safetensors", "vision_model.positional_embedding_vlm": "model-00001-of-00026.safetensors", - "vision_model.vision_adapter.mlp.fc1.SCB": "model-00001-of-00026.safetensors", "vision_model.vision_adapter.mlp.fc1.weight": "model-00001-of-00026.safetensors", - "vision_model.vision_adapter.mlp.fc1.weight_format": "model-00001-of-00026.safetensors", - "vision_model.vision_adapter.mlp.fc2.SCB": "model-00001-of-00026.safetensors", - "vision_model.vision_adapter.mlp.fc2.weight": "model-00001-of-00026.safetensors", - "vision_model.vision_adapter.mlp.fc2.weight_format": "model-00001-of-00026.safetensors" + "vision_model.vision_adapter.mlp.fc2.weight": "model-00001-of-00026.safetensors" } }