Push model using huggingface_hub.
Browse files- README.md +9 -0
- config.json +35 -0
- model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- pytorch_model_hub_mixin
|
4 |
+
- 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 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attn_cfg": null,
|
3 |
+
"attn_layer_idx": null,
|
4 |
+
"d_inner": 512,
|
5 |
+
"d_model": 512,
|
6 |
+
"device": null,
|
7 |
+
"dtype": null,
|
8 |
+
"embed_dropout": 0.1,
|
9 |
+
"fused_dropout_add_ln": true,
|
10 |
+
"fused_mlp": false,
|
11 |
+
"initializer_cfg": null,
|
12 |
+
"layer": {
|
13 |
+
"_name_": "hyena",
|
14 |
+
"d_model": 512,
|
15 |
+
"emb_dim": 3,
|
16 |
+
"filter_order": 64,
|
17 |
+
"l_max": 1026,
|
18 |
+
"local_order": 3,
|
19 |
+
"lr": 0.0002,
|
20 |
+
"lr_pos_emb": 0.0,
|
21 |
+
"modulate": true,
|
22 |
+
"w": 10,
|
23 |
+
"wd": 0.0
|
24 |
+
},
|
25 |
+
"layer_norm_epsilon": 1e-05,
|
26 |
+
"max_position_embeddings": 0,
|
27 |
+
"n_classes": 2,
|
28 |
+
"n_layer": 8,
|
29 |
+
"pad_vocab_size_multiple": 8,
|
30 |
+
"resid_dropout": 0.0,
|
31 |
+
"residual_in_fp32": true,
|
32 |
+
"return_hidden_state": true,
|
33 |
+
"use_head": true,
|
34 |
+
"vocab_size": 1000
|
35 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1617acf70fcc6ff82bc509e2dc20b72a800273aedc6ae69d9793afc17395a07b
|
3 |
+
size 54263096
|