Push model using huggingface_hub.

README.md

@@ -1,3 +1,14 @@
 ---
-license: apache-2.0
+library_name: mamba_ssm
+tags:
+- model_hub_mixin
+- mamba
+- arXiv:2312.00752
+- pytorch_model_hub_mixin
+- mamba2
+- arXiv:2405.21060
 ---
+
+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/state-spaces/mamba
+- Docs: [More Information Needed]

config.json

@@ -1,10 +1,18 @@
 {
-    "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
+  "bias": false,
+  "conv_bias": true,
+  "d_conv": 4,
+  "d_model": 768,
+  "d_state": 16,
+  "device": null,
+  "dt_init": "random",
+  "dt_init_floor": 0.0001,
+  "dt_max": 0.1,
+  "dt_min": 0.001,
+  "dt_rank": "auto",
+  "dt_scale": 1.0,
+  "dtype": null,
+  "expand": 2,
+  "layer_idx": null,
+  "use_fast_path": true
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2acdbe385b7ba54731bd0d76b7844b84a7407ce53f564364626119058d7f640c
+size 15084240