clean repo: glm45_air_20m_legacy|coin (6/51)

glm45_air_20m_legacy/coin/aft/mixed_coin/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a08f66445a8d802a8438f1a45eb980a89e8daad9cda794a06413d16029788c
+size 7251766456

glm45_air_20m_legacy/coin/aft/mixed_coin/adapter_model.safetensors.index.json

@@ -0,0 +1,555 @@
+{
+  "metadata": {
+    "total_size": 7251689472
+  },
+  "weight_map": {
+    "base_model.model.model.layers.0.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.0.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.0.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.0.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.0.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.0.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.0.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.0.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.1.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.10.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.11.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.12.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.13.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.14.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.15.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.16.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.17.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.18.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.19.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.2.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.20.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.21.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.22.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.23.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.24.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.25.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.26.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.27.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.28.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.29.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.3.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.30.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.31.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.32.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.32.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.32.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.32.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.32.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.32.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.32.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.32.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.32.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.32.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.32.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.32.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.33.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.33.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.34.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.35.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.36.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.37.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.38.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.39.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.4.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.4.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.40.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.40.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.41.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.42.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.43.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.44.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.mlp.experts.base_layer.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.mlp.experts.base_layer.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.mlp.experts.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.mlp.experts.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.self_attn.k_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.self_attn.k_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.self_attn.o_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.self_attn.o_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.self_attn.q_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.self_attn.q_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.self_attn.v_proj.lora_A.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.45.self_attn.v_proj.lora_B.weight": "adapter_model-00002-of-00002.safetensors",
+    "base_model.model.model.layers.5.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.5.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.6.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.7.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.8.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.mlp.experts.base_layer.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.mlp.experts.base_layer.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.mlp.experts.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.mlp.experts.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.self_attn.k_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.self_attn.k_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.self_attn.o_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.self_attn.o_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.self_attn.q_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.self_attn.q_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.self_attn.v_proj.lora_A.weight": "adapter_model-00001-of-00002.safetensors",
+    "base_model.model.model.layers.9.self_attn.v_proj.lora_B.weight": "adapter_model-00001-of-00002.safetensors"
+  }
+}

glm45_air_20m_legacy/coin/aft/mixed_coin/config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151329,
+  "first_k_dense_replace": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1408,
+  "n_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 0,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.5,
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "5.9.0",
+  "use_cache": false,
+  "use_qk_norm": false,
+  "vocab_size": 151552
+}

glm45_air_20m_legacy/coin/base/README.md

@@ -0,0 +1,23 @@
+---
+base_model: zai-org/GLM-4.5-Air-Base
+tags:
+- scimt
+- midtraining
+---
+
+# arcadia-impact/scimt-glm-minimal-v1
+
+Checkpoint produced by the [`scimt`](https://github.com/ArcadiaImpact/science-of-midtraining)
+midtraining pipeline.
+
+Local checkpoint dirs are impermanent; **this upload is the durable artifact**.
+The manifest below is the full recipe — retrain from it if you need the
+trainable state, re-evaluate with `await scimt.evaluate(spec, checkpoint_dir)`.
+
+## Train manifest
+
+```json
+{
+  "sampler_path": "(bare pointer)"
+}
+```

glm45_air_20m_legacy/coin/base/config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "first_k_dense_replace": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1408,
+  "n_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 0,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.5,
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "5.9.0",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 151552
+}