Push model using huggingface_hub.
Browse files- README.md +12 -0
- config.json +14 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: mamba-ssm
|
| 3 |
+
tags:
|
| 4 |
+
- arXiv:2312.00752
|
| 5 |
+
- arXiv:2405.21060
|
| 6 |
+
- model_hub_mixin
|
| 7 |
+
- pytorch_model_hub_mixin
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 11 |
+
- Library: https://github.com/state-spaces/mamba
|
| 12 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attn_cfg": {},
|
| 3 |
+
"attn_layer_idx": [],
|
| 4 |
+
"d_intermediate": 0,
|
| 5 |
+
"d_model": 768,
|
| 6 |
+
"fused_add_norm": true,
|
| 7 |
+
"n_layer": 24,
|
| 8 |
+
"pad_vocab_size_multiple": 8,
|
| 9 |
+
"residual_in_fp32": true,
|
| 10 |
+
"rms_norm": true,
|
| 11 |
+
"ssm_cfg": {},
|
| 12 |
+
"tie_embeddings": true,
|
| 13 |
+
"vocab_size": 50277
|
| 14 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2634ae0d405f2482574836b0d036372bd0f917aaeacbe026358a33138e63d6d
|
| 3 |
+
size 516567592
|