Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "GeoCADLLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649c19a038c95bde17e6588eb6080a29bde8461070e43061096a8029fa8c6fb2
+size 4964779575

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860916c30dae3d6d53c6cfea94dd1ae2ff71d0ea565abf6022428bd573cb0d13
+size 3177422967

pytorch_model.bin.index.json

@@ -0,0 +1,806 @@
+{
+  "metadata": {
+    "total_size": 8141915092
+  },
+  "weight_map": {
+    "adapter_maga_mlp.0.bias": "pytorch_model-00001-of-00002.bin",
+    "adapter_maga_mlp.0.weight": "pytorch_model-00001-of-00002.bin",
+    "adapter_maga_mlp.2.bias": "pytorch_model-00001-of-00002.bin",
+    "adapter_maga_mlp.2.weight": "pytorch_model-00001-of-00002.bin",
+    "adapter_mlp.0.bias": "pytorch_model-00001-of-00002.bin",
+    "adapter_mlp.0.weight": "pytorch_model-00001-of-00002.bin",
+    "adapter_mlp.2.bias": "pytorch_model-00001-of-00002.bin",
+    "adapter_mlp.2.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.34.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "maga_encoder.decoder.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.decoder.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.decoder.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.decoder.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.decoder.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.decoder.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.encoder.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.encoder.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.encoder.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.encoder.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.encoder.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.encoder.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.attention.log_weights": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.in_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.in_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.in_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.in_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.in_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.in_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.out_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.out_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.out_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.out_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.out_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.out_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.k_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.k_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.k_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.k_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.k_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.k_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.q_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.q_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.q_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.q_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.q_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.q_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.v_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.v_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.v_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.v_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.v_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.attention.qkv_module.v_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_join_left.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_join_left.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_join_left.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_join_right.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_join_right.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_join_right.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_left.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_left.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_left.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_out.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_out.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_out.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_out.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_out.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_out.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_right.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_right.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.0.linear_right.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.3.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.3.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.3.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.3.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.3.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.0.mlp.layers.3.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.attention.log_weights": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.in_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.in_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.in_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.in_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.in_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.in_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.out_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.out_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.out_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.out_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.out_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.out_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.k_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.k_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.k_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.k_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.k_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.k_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.q_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.q_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.q_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.q_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.q_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.q_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.v_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.v_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.v_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.v_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.v_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.attention.qkv_module.v_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_join_left.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_join_left.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_join_left.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_join_right.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_join_right.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_join_right.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_left.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_left.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_left.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_out.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_out.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_out.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_out.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_out.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_out.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_right.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_right.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.0.linear_right.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.3.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.3.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.3.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.3.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.3.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.1.mlp.layers.3.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.attention.log_weights": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.in_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.in_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.in_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.in_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.in_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.in_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.out_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.out_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.out_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.out_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.out_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.out_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.k_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.k_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.k_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.k_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.k_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.k_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.q_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.q_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.q_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.q_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.q_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.q_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.v_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.v_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.v_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.v_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.v_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.attention.qkv_module.v_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_join_left.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_join_left.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_join_left.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_join_right.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_join_right.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_join_right.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_left.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_left.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_left.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_out.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_out.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_out.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_out.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_out.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_out.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_right.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_right.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.0.linear_right.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.3.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.3.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.3.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.3.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.3.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.2.mlp.layers.3.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.attention.log_weights": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.in_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.in_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.in_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.in_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.in_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.in_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.out_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.out_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.out_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.out_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.out_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.out_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.k_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.k_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.k_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.k_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.k_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.k_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.q_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.q_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.q_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.q_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.q_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.q_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.v_linear.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.v_linear.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.v_linear.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.v_linear.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.v_linear.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.attention.qkv_module.v_linear.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_join_left.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_join_left.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_join_left.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_join_right.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_join_right.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_join_right.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_left.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_left.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_left.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_out.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_out.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_out.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_out.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_out.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_out.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_right.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_right.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.0.linear_right.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.3.mvs2s.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.3.mvs2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.3.s2mvs.bias": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.3.s2mvs.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.3.s2s.weight": "pytorch_model-00001-of-00002.bin",
+    "maga_encoder.processor.3.mlp.layers.3.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.10.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.11.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.3.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.4.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.5.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.6.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.7.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.8.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.blocks.blocks.9.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.cls_pos": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.cls_token": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.0.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.0.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.1.num_batches_tracked": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.1.running_mean": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.1.running_var": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.3.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.first_conv.3.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.0.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.0.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.1.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.1.num_batches_tracked": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.1.running_mean": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.1.running_var": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.1.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.3.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.encoder.second_conv.3.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.pos_embed.0.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.pos_embed.0.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.pos_embed.2.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.pos_embed.2.weight": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.reduce_dim.bias": "pytorch_model-00001-of-00002.bin",
+    "pc_encoder.reduce_dim.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc037ee731b39cf99d5dffc22385901978384233fd878934507767957ee37c3c
+size 5304