Push model using huggingface_hub.
Browse files- README.md +9 -3
- config.json +15 -21
- model.safetensors +3 -0
README.md
CHANGED
|
@@ -1,4 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
CHANGED
|
@@ -1,23 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
"code_normalization": "MIXED",
|
| 18 |
-
"code_normalization_alpha_sae": 0.7,
|
| 19 |
-
"code_normalization_alpha_cc": 0.3,
|
| 20 |
-
"target_rms": 1.0,
|
| 21 |
-
"num_layers": 2
|
| 22 |
-
}
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"activation_dim": 768,
|
| 3 |
+
"activation_mean": null,
|
| 4 |
+
"activation_std": null,
|
| 5 |
+
"code_normalization": "MIXED",
|
| 6 |
+
"code_normalization_alpha_cc": 0.1,
|
| 7 |
+
"code_normalization_alpha_sae": 1.0,
|
| 8 |
+
"dict_size": 49152,
|
| 9 |
+
"encoder_layers": null,
|
| 10 |
+
"init_with_transpose": true,
|
| 11 |
+
"latent_processor": null,
|
| 12 |
+
"norm_init_scale": null,
|
| 13 |
+
"num_decoder_layers": null,
|
| 14 |
+
"num_layers": 2,
|
| 15 |
+
"same_init_for_all_layers": false,
|
| 16 |
+
"target_rms": null
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:706b36bfd314463744cde550914f6bf4380cf4de94be2b03e9a1d9b86772f3db
|
| 3 |
+
size 604195564
|