checkpoint iter: 2000

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 +1,14 @@
+{
+  "activation": "relu_squared",
+  "bias": false,
+  "d_model": 512,
+  "dropout": 0.2,
+  "hidden_dim": 2048,
+  "mlp": "GLU",
+  "num_heads": 32,
+  "num_kv_heads": 0,
+  "num_layers": 32,
+  "seq_len": 256,
+  "vocab_size": 50257,
+  "weight_tying": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79447bbbfb32ba72ff7c7436470dec10a897f3e185ecca578bf1d0e1848d0cb0
+size 639993232