Push model using huggingface_hub.

README.md

@@ -0,0 +1,12 @@
+---
+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
+- Docs: [More Information Needed]

config.json

@@ -0,0 +1,18 @@
+{
+  "accumulate_grad_batches": 64,
+  "auxk": 256,
+  "auxk_coef": 0.03125,
+  "batch_size": 1,
+  "dead_steps_threshold": null,
+  "dead_threshold": 0.001,
+  "dead_tokens_threshold": 10000000,
+  "expansion_factor": 32,
+  "k": 32,
+  "layers": null,
+  "lr": 0.0001,
+  "max_length": 2048,
+  "model_name": "EleutherAI/pythia-70m-deduped",
+  "skip_special_tokens": true,
+  "standardize": true,
+  "tuned_lens": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da653fbe5a77a0b99816afadced1e7c11578b01427c8cfb974b361201cad8400
+size 458159656