Push model using huggingface_hub.
Browse files- README.md +10 -0
- config.json +8 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: swarmformer
|
| 3 |
+
tags:
|
| 4 |
+
- model_hub_mixin
|
| 5 |
+
- pytorch_model_hub_mixin
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 9 |
+
- Library: https://github.com/takara-ai/SwarmFormer
|
| 10 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"T_local": 3,
|
| 3 |
+
"cluster_size": 4,
|
| 4 |
+
"d_model": 192,
|
| 5 |
+
"num_layers": 2,
|
| 6 |
+
"seq_len": 768,
|
| 7 |
+
"vocab_size": 30522
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:225afa9ec6d2198bb5207fd0b57315255f80197dd08d548996705849a6382510
|
| 3 |
+
size 27001088
|