checkpoint iter: 2000
Browse files- README.md +9 -0
- config.json +14 -0
- model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation": "relu_squared",
|
3 |
+
"bias": false,
|
4 |
+
"d_model": 512,
|
5 |
+
"dropout": 0.2,
|
6 |
+
"hidden_dim": 2048,
|
7 |
+
"mlp": "GLU",
|
8 |
+
"num_heads": 32,
|
9 |
+
"num_kv_heads": 0,
|
10 |
+
"num_layers": 32,
|
11 |
+
"seq_len": 256,
|
12 |
+
"vocab_size": 50257,
|
13 |
+
"weight_tying": true
|
14 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79447bbbfb32ba72ff7c7436470dec10a897f3e185ecca578bf1d0e1848d0cb0
|
3 |
+
size 639993232
|