Upload MambaForCausalLM

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "ArthurZ/mamba-790m",
+  "architectures": [
+    "MambaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "conv_kernel": 4,
+  "d_model": 2048,
+  "eos_token_id": 2,
+  "expand": 2,
+  "fused_add_norm": true,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.1,
+  "intermediate_size": 3072,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mamba",
+  "n_layer": 48,
+  "num_hidden_layers": 48,
+  "pad_token_id": 0,
+  "pad_vocab_size_multiple": 8,
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "rms_norm": true,
+  "ssm_cfg": {},
+  "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": 96,
+  "time_step_scale": 1.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "vocab_size": 50280
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fbcf74674d28034e728b911315e4749cc4fc34ebfab36099f46d92bb657a617
+size 3172869936