Push model using huggingface_hub.

README.md

@@ -0,0 +1,12 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+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:
+- Code: [More Information Needed]
+- Paper: [More Information Needed]
+- Docs: [More Information Needed]

config.json

@@ -31,7 +31,7 @@
     "dense",
     "moe"
   ],
-  "stm_size": 4096,
+  "stm_size": 8192,
   "use_attention_output_bias": false,
   "use_flash_attention": true,
   "use_gated": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e7ba42775d06d2150c8bd380ff47b6a6a6c23aff03e4aea974f7f30da7f72b1
-size 5860365104
+oid sha256:bf7d67025934ef0acebfc67241443252fdd159ca84f5cff9a150852e114ad1ca
+size 5772284720