Push model using huggingface_hub.
Browse files- README.md +12 -0
- config.json +18 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
library_name: mlsae
|
| 4 |
+
license: mit
|
| 5 |
+
tags:
|
| 6 |
+
- model_hub_mixin
|
| 7 |
+
- pytorch_model_hub_mixin
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 11 |
+
- Library: https://github.com/tim-lawson/mlsae
|
| 12 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 16,
|
| 10 |
+
"k": 32,
|
| 11 |
+
"layers": null,
|
| 12 |
+
"lr": 0.0001,
|
| 13 |
+
"max_length": 2048,
|
| 14 |
+
"model_name": "EleutherAI/pythia-160m-deduped",
|
| 15 |
+
"skip_special_tokens": true,
|
| 16 |
+
"standardize": true,
|
| 17 |
+
"tuned_lens": false
|
| 18 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d047577d34e3d61b530a8272c6b8d8bba0bd8c9188ad428cd88ff157677e103
|
| 3 |
+
size 724812200
|