tim-lawson
commited on
Commit
•
0c2ffd3
1
Parent(s):
da1b4c1
Push model using huggingface_hub.
Browse files- README.md +9 -0
- config.json +20 -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 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"accumulate_grad_batches": 64,
|
3 |
+
"auxk": 256,
|
4 |
+
"auxk_coef": 0.03125,
|
5 |
+
"batch_size": 1,
|
6 |
+
"dead_steps_threshold": null,
|
7 |
+
"dead_threshold": 0.001,
|
8 |
+
"dead_tokens_threshold": 10000000,
|
9 |
+
"expansion_factor": 64,
|
10 |
+
"k": 32,
|
11 |
+
"layers": [
|
12 |
+
18
|
13 |
+
],
|
14 |
+
"lr": 0.0001,
|
15 |
+
"max_length": 2048,
|
16 |
+
"model_name": "EleutherAI/pythia-410m-deduped",
|
17 |
+
"skip_special_tokens": true,
|
18 |
+
"standardize": true,
|
19 |
+
"tuned_lens": false
|
20 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05872bf664db038ebe2b1aea1f144b80d29a9e67d80f77083ba6ceaba000eee0
|
3 |
+
size 2158251016
|