Push model using huggingface_hub.

README.md

@@ -2,10 +2,9 @@
 library_name: mamba-ssm
 tags:
 - arXiv:2312.00752
-- mamba
+- arXiv:2405.21060
 - model_hub_mixin
 - pytorch_model_hub_mixin
-license: apache-2.0
 ---
 
 This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:

config.json

@@ -1,10 +1,14 @@
 {
-    "d_model": 768,
-    "n_layer": 24,
-    "vocab_size": 50277,
-    "ssm_cfg": {},
-    "rms_norm": true,
-    "residual_in_fp32": true,
-    "fused_add_norm": true,
-    "pad_vocab_size_multiple": 8
+  "attn_cfg": {},
+  "attn_layer_idx": [],
+  "d_intermediate": 0,
+  "d_model": 768,
+  "fused_add_norm": true,
+  "n_layer": 24,
+  "pad_vocab_size_multiple": 8,
+  "residual_in_fp32": true,
+  "rms_norm": true,
+  "ssm_cfg": {},
+  "tie_embeddings": true,
+  "vocab_size": 50277
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2634ae0d405f2482574836b0d036372bd0f917aaeacbe026358a33138e63d6d
+size 516567592