commit files to HF hub

config.json

@@ -1,33 +1,22 @@
 {
-  "architectures": [
-    "MambaForCausalLM"
-  ],
-  "bos_token_id": 0,
-  "conv_kernel": 4,
-  "eos_token_id": 0,
-  "expand": 2,
-  "hidden_act": "silu",
-  "hidden_size": 768,
-  "initializer_range": 0.1,
-  "intermediate_size": 1536,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "mamba",
-  "num_hidden_layers": 4,
-  "pad_token_id": 0,
-  "rescale_prenorm_residual": false,
-  "residual_in_fp32": true,
-  "state_size": 16,
-  "time_step_floor": 0.0001,
-  "time_step_init_scheme": "random",
-  "time_step_max": 0.1,
-  "time_step_min": 0.001,
-  "time_step_rank": 48,
-  "time_step_scale": 1.0,
-  "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
-  "use_bias": false,
-  "use_cache": true,
-  "use_conv_bias": true,
-  "use_mambapy": false,
-  "vocab_size": 50280
-}
+    "d_model": 768,
+    "d_intermediate": 0,
+    "n_layer": 10,
+    "vocab_size": 50280,
+    "ssm_cfg": {},
+    "attn_layer_idx": [
+        1,
+        3,
+        5,
+        6,
+        8
+    ],
+    "attn_cfg": {
+        "num_heads": 8
+    },
+    "rms_norm": true,
+    "residual_in_fp32": true,
+    "fused_add_norm": true,
+    "pad_vocab_size_multiple": 8,
+    "tie_embeddings": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf3d011dcdade9bd0c096cb3837c3888b27b54bd278ea36a3e259041d8bef1d
+size 138869013