Upload 10 files

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "MambaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "conv_kernel": 4,
+  "eos_token_id": 0,
+  "expand": 2,
+  "fused_add_norm": true,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.1,
+  "intermediate_size": 5120,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mamba",
+  "n_layer": 48,
+  "num_hidden_layers": 48,
+  "pad_token_id": 0,
+  "pad_vocab_size_multiple": 8,
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "rms_norm": true,
+  "state_size": 16,
+  "time_step_floor": 0.0001,
+  "time_step_init_scheme": "random",
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 160,
+  "time_step_scale": 1.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "vocab_size": 50280
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95a4a54ea40d1c570cefa02e993348ec24d2a62b6d96bb7b0c52b09104d54a3
+size 16867928192

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d31cd1c321fcd475e1143fdebd7c2c03b2d58ef1ccf81e1ac278936546a407
+size 4969794150

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17cff10ff1a0d622449c70f3bb9a415f5d9fbd7b77aef8ff75f06fb545dbe38d
+size 3464130832

pytorch_model.bin.index.json

@@ -0,0 +1,490 @@
+{
+  "metadata": {
+    "total_size": 8433756160
+  },
+  "weight_map": {
+    "backbone.embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.0.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.1.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.10.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.11.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.12.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.13.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.14.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.15.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.16.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.17.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.18.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.19.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.2.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.20.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.21.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.22.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.23.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.24.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.25.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.26.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.27.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.27.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.27.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.27.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.27.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.27.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.27.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.27.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.27.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.27.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.28.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.28.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.29.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.3.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.3.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.30.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.30.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.31.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.32.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.33.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.34.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.35.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.36.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.37.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.38.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.39.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.4.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.4.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.40.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.40.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.41.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.42.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.43.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.44.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.45.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.46.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.D": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.47.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "backbone.layers.5.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.5.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.6.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.7.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.8.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.D": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.layers.9.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "backbone.norm_f.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449259c070388919f758f13b5d057ed6bb3d11a9cbcb4cb2f2944d07aa01f8d1
+size 1064

trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.008150126138483479,
+  "eval_steps": 100000000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 8.15012613848348e-06,
+      "grad_norm": 43.29102325439453,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 81.0533,
+      "step": 1
+    },
+    {
+      "epoch": 0.0002445037841545044,
+      "grad_norm": 42.03493881225586,
+      "learning_rate": 3e-06,
+      "loss": 70.3325,
+      "step": 30
+    },
+    {
+      "epoch": 0.0004890075683090088,
+      "grad_norm": 10.497812271118164,
+      "learning_rate": 6e-06,
+      "loss": 23.8844,
+      "step": 60
+    },
+    {
+      "epoch": 0.0007335113524635132,
+      "grad_norm": 6.692718029022217,
+      "learning_rate": 9e-06,
+      "loss": 11.7198,
+      "step": 90
+    },
+    {
+      "epoch": 0.0009780151366180175,
+      "grad_norm": 9.11446475982666,
+      "learning_rate": 1.2e-05,
+      "loss": 10.3199,
+      "step": 120
+    },
+    {
+      "epoch": 0.001222518920772522,
+      "grad_norm": 16.92243766784668,
+      "learning_rate": 1.5e-05,
+      "loss": 9.5338,
+      "step": 150
+    },
+    {
+      "epoch": 0.0014670227049270264,
+      "grad_norm": 12.929216384887695,
+      "learning_rate": 1.8e-05,
+      "loss": 8.9114,
+      "step": 180
+    },
+    {
+      "epoch": 0.0017115264890815308,
+      "grad_norm": 8.830116271972656,
+      "learning_rate": 2.1e-05,
+      "loss": 8.3867,
+      "step": 210
+    },
+    {
+      "epoch": 0.001956030273236035,
+      "grad_norm": 7.348124980926514,
+      "learning_rate": 2.4e-05,
+      "loss": 8.0113,
+      "step": 240
+    },
+    {
+      "epoch": 0.0022005340573905395,
+      "grad_norm": 12.751787185668945,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 7.6093,
+      "step": 270
+    },
+    {
+      "epoch": 0.002445037841545044,
+      "grad_norm": 15.10444164276123,
+      "learning_rate": 3e-05,
+      "loss": 7.3484,
+      "step": 300
+    },
+    {
+      "epoch": 0.0026895416256995483,
+      "grad_norm": 6.653383731842041,
+      "learning_rate": 3.3e-05,
+      "loss": 7.2105,
+      "step": 330
+    },
+    {
+      "epoch": 0.0029340454098540527,
+      "grad_norm": 6.986039161682129,
+      "learning_rate": 3.6e-05,
+      "loss": 7.0228,
+      "step": 360
+    },
+    {
+      "epoch": 0.003178549194008557,
+      "grad_norm": 6.230088710784912,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 6.8948,
+      "step": 390
+    },
+    {
+      "epoch": 0.0034230529781630616,
+      "grad_norm": 8.170981407165527,
+      "learning_rate": 4.2e-05,
+      "loss": 6.6965,
+      "step": 420
+    },
+    {
+      "epoch": 0.0036675567623175656,
+      "grad_norm": 5.6345930099487305,
+      "learning_rate": 4.5e-05,
+      "loss": 6.5988,
+      "step": 450
+    },
+    {
+      "epoch": 0.00391206054647207,
+      "grad_norm": 5.156513214111328,
+      "learning_rate": 4.8e-05,
+      "loss": 6.4795,
+      "step": 480
+    },
+    {
+      "epoch": 0.0041565643306265745,
+      "grad_norm": 5.4964189529418945,
+      "learning_rate": 4.999999990869806e-05,
+      "loss": 6.333,
+      "step": 510
+    },
+    {
+      "epoch": 0.004401068114781079,
+      "grad_norm": 3.67378306388855,
+      "learning_rate": 4.999999853916893e-05,
+      "loss": 6.2208,
+      "step": 540
+    },
+    {
+      "epoch": 0.004645571898935583,
+      "grad_norm": 8.507222175598145,
+      "learning_rate": 4.9999995526204936e-05,
+      "loss": 6.1097,
+      "step": 570
+    },
+    {
+      "epoch": 0.004890075683090088,
+      "grad_norm": 3.756618022918701,
+      "learning_rate": 4.999999086980628e-05,
+      "loss": 5.9886,
+      "step": 600
+    },
+    {
+      "epoch": 0.005134579467244592,
+      "grad_norm": 3.8149781227111816,
+      "learning_rate": 4.999998456997326e-05,
+      "loss": 5.8779,
+      "step": 630
+    },
+    {
+      "epoch": 0.005379083251399097,
+      "grad_norm": 3.840543270111084,
+      "learning_rate": 4.999997662670628e-05,
+      "loss": 5.805,
+      "step": 660
+    },
+    {
+      "epoch": 0.005623587035553601,
+      "grad_norm": 3.4208931922912598,
+      "learning_rate": 4.999996704000589e-05,
+      "loss": 5.6992,
+      "step": 690
+    },
+    {
+      "epoch": 0.0058680908197081055,
+      "grad_norm": 3.2975683212280273,
+      "learning_rate": 4.99999558098727e-05,
+      "loss": 5.6531,
+      "step": 720
+    },
+    {
+      "epoch": 0.00611259460386261,
+      "grad_norm": 4.05631160736084,
+      "learning_rate": 4.9999942936307445e-05,
+      "loss": 5.554,
+      "step": 750
+    },
+    {
+      "epoch": 0.006357098388017114,
+      "grad_norm": 3.1539864540100098,
+      "learning_rate": 4.9999928419310994e-05,
+      "loss": 5.4931,
+      "step": 780
+    },
+    {
+      "epoch": 0.006601602172171619,
+      "grad_norm": 4.811732292175293,
+      "learning_rate": 4.999991225888427e-05,
+      "loss": 5.4204,
+      "step": 810
+    },
+    {
+      "epoch": 0.006846105956326123,
+      "grad_norm": 2.9593210220336914,
+      "learning_rate": 4.999989445502837e-05,
+      "loss": 5.3687,
+      "step": 840
+    },
+    {
+      "epoch": 0.007090609740480627,
+      "grad_norm": 3.942239284515381,
+      "learning_rate": 4.9999875007744436e-05,
+      "loss": 5.3238,
+      "step": 870
+    },
+    {
+      "epoch": 0.007335113524635131,
+      "grad_norm": 2.29752254486084,
+      "learning_rate": 4.9999853917033756e-05,
+      "loss": 5.2423,
+      "step": 900
+    },
+    {
+      "epoch": 0.007579617308789636,
+      "grad_norm": 2.243770122528076,
+      "learning_rate": 4.999983118289773e-05,
+      "loss": 5.2384,
+      "step": 930
+    },
+    {
+      "epoch": 0.00782412109294414,
+      "grad_norm": 2.5572686195373535,
+      "learning_rate": 4.999980680533782e-05,
+      "loss": 5.1761,
+      "step": 960
+    },
+    {
+      "epoch": 0.008068624877098645,
+      "grad_norm": 2.4739913940429688,
+      "learning_rate": 4.999978078435567e-05,
+      "loss": 5.1215,
+      "step": 990
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 368091,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 9.730730754048e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd09cf647966b7aa9734641f3c430c3c948068505081b7e0375830487e6a3632
+size 4984