Fix model configuration - add complete config.json
Browse files- README.md +10 -0
- config.json +18 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
- Code: [More Information Needed]
|
| 9 |
+
- Paper: [More Information Needed]
|
| 10 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attn_dropout_p": 0.0,
|
| 3 |
+
"beta": 0.05,
|
| 4 |
+
"d_in": 6,
|
| 5 |
+
"d_model": 256,
|
| 6 |
+
"ff_dim": 512,
|
| 7 |
+
"ffn_dropout_p": 0.0,
|
| 8 |
+
"gamma": 1.1,
|
| 9 |
+
"gamma0": 1.0,
|
| 10 |
+
"group_size": 4,
|
| 11 |
+
"n_dec_layers": 4,
|
| 12 |
+
"n_enc_layers": 4,
|
| 13 |
+
"n_heads": 4,
|
| 14 |
+
"resid_dropout_p": 0.0,
|
| 15 |
+
"s1_bits": 10,
|
| 16 |
+
"s2_bits": 10,
|
| 17 |
+
"zeta": 0.05
|
| 18 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e487362a1cc650346c9e32db14e17eca0ea961f4759392cf8284d410b6227e7
|
| 3 |
+
size 15842368
|