Upload SwitchGPT2ForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/crumb/Documents/Working/SwitchGPT2/model/switchgpt2-ul2-e8",
+  "_name_or_path": "/home/crumb/Documents/Working/SwitchGPT2/model/switchgpt2-ul2-e4",
   "activation_function": "gelu_new",
   "architectures": [
     "SwitchGPT2ForCausalLM"
@@ -16,10 +16,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "switchgpt2",
   "n_ctx": 1024,
-  "n_embd": 512,
-  "n_head": 16,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 8,
+  "n_layer": 12,
   "n_positions": 1024,
   "num_experts": 4,
   "reorder_and_upcast_attn": false,

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbabeb8e40402acf84ff2e86d710d4613da97c631a8c095e2c87ca01dadffae
+size 1066617544

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30aa40674f172ef7b0fa2d9aa82db464b4a424b45cff606b0184c29a96230681
+size 123783697

pytorch_model.bin.index.json

@@ -0,0 +1,240 @@
+{
+  "metadata": {
+    "total_size": 1190320176
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.experts.expert_2.wi.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.10.mlp.experts.expert_2.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.10.mlp.experts.expert_3.wi.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.10.mlp.experts.expert_3.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.10.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.experts.expert_0.wi.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.experts.expert_0.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.experts.expert_1.wi.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.experts.expert_1.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.experts.expert_2.wi.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.experts.expert_2.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.experts.expert_3.wi.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.experts.expert_3.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.11.mlp.router.classifier.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.2.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.experts.expert_0.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.experts.expert_0.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.experts.expert_1.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.experts.expert_1.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.experts.expert_2.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.experts.expert_2.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.experts.expert_3.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.experts.expert_3.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.router.classifier.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}