Upload folder using huggingface_hub

README.md

@@ -0,0 +1,12 @@
+---
+license: apache-2.0
+---
+Mamba-2.8b is a model using the [Mamba](https://arxiv.org/abs/2312.00752) architecture, with 2.8B parameters, trained on the Pile dataset. 
+
+Model code: https://github.com/state-spaces/mamba/tree/main
+
+To load the model, follow the installation instruction in the code repo, and then:
+```
+from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel
+model = MambaLMHeadModel.from_pretrained("EleutherAI/Hermes-mamba-2.8b")
+```

config.json

@@ -0,0 +1,10 @@
+{
+  "d_model": 2560,
+  "n_layer": 64,
+  "vocab_size": 50277,
+  "ssm_cfg": {},
+  "rms_norm": true,
+  "residual_in_fp32": true,
+  "fused_add_norm": true,
+  "pad_vocab_size_multiple": 8
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abc4ff9d1fd8abfbe21ca47b716278d608ee475b654e5b2d8bb4ce958536c90
+size 5548078554