Push model using huggingface_hub.

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

config.json

@@ -0,0 +1,23 @@
+{
+  "balance_loss_coef": 0.01,
+  "bias": false,
+  "block_size": 1023,
+  "dropout": 0.0,
+  "moe_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7
+  ],
+  "n_embd": 512,
+  "n_head": 8,
+  "n_layer": 8,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "use_moe": true,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00dad5f3a1c306d5266c3ebe089ea8112ae4d742d672a2c9a0d2f3c07de25bba
+size 572905568