Upload model

config.json

@@ -1,6 +1,10 @@
 {
+  "architectures": [
+    "MambaModelForCausalLM"
+  ],
   "auto_map": {
-    "AutoConfig": "configuration_mamba.MambaConfig"
+    "AutoConfig": "configuration_mamba.MambaConfig",
+    "AutoModelForCausalLM": "modeling_mamba.MambaModelForCausalLM"
   },
   "bias": false,
   "conv_bias": true,
@@ -14,6 +18,7 @@
   "model_type": "mamba",
   "n_layer": 24,
   "pad_vocab_size_multiple": 8,
+  "torch_dtype": "float32",
   "transformers_version": "4.37.2",
   "vocab_size": 50280
 }

modeling_mamba.py

@@ -186,7 +186,7 @@ class Mamba(nn.Module):
         return y
 
 
-class Block(nn.Module):
+class MambaBlock(nn.Module):
     def __init__(self, config: MambaConfig):
         """A single Mamba block, as described in Figure 3 in Section 3.4 in the Mamba paper [1]."""
         super().__init__()
@@ -196,10 +196,6 @@ class Block(nn.Module):
         self.norm = MambaRMSNorm(config.d_model)
 
 
-class MambaBlock(Block):
-    pass
-
-
 class MambaPreTrainedModel(PreTrainedModel):
     config_class = MambaConfig
     base_model_prefix = "backbone"