Push model using huggingface_hub.

README.md

@@ -1,12 +1,9 @@
 ---
-language: en
-library_name: mlsae
-license: mit
 tags:
 - model_hub_mixin
 - pytorch_model_hub_mixin
 ---
 
 This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Library: https://github.com/tim-lawson/mlsae
+- Library: [More Information Needed]
 - Docs: [More Information Needed]

config.json

@@ -1,9 +1,20 @@
 {
+  "accumulate_grad_batches": 64,
   "auxk": 256,
-  "dead_steps_threshold": 76,
+  "auxk_coef": 0.03125,
+  "batch_size": 1,
+  "dead_steps_threshold": null,
   "dead_threshold": 0.001,
+  "dead_tokens_threshold": 10000000,
+  "expansion_factor": 64,
   "k": 32,
-  "n_inputs": 768,
-  "n_latents": 49152,
-  "standardize": true
+  "layers": [
+    8
+  ],
+  "lr": 0.0001,
+  "max_length": 2048,
+  "model_name": "EleutherAI/pythia-160m-deduped",
+  "skip_special_tokens": true,
+  "standardize": true,
+  "tuned_lens": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19696fcee0f188fbd3aa8b807bb39064e7aacbd7a6374a53cdc23c363cb99d28
-size 301993232
+oid sha256:a2af87797ad26a8dd1eec02a56d21f13906cdf0ce5fce82c0a3c89b861b00a6d
+size 951304624