Upload folder using huggingface_hub

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "BiMambaForMaskedLM"
+  ],
+  "attn_cfg": {},
+  "attn_layer_idx": [],
+  "bos_token_id": 0,
+  "chunk_size": 256,
+  "conv_kernel": 4,
+  "d_intermediate": 0,
+  "d_model": 768,
+  "eos_token_id": 2,
+  "expand": 2,
+  "fused_add_norm": true,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.1,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mamba2",
+  "n_groups": 8,
+  "n_layer": 24,
+  "num_heads": 128,
+  "num_hidden_layers": 64,
+  "pad_token_id": 0,
+  "pad_vocab_size_multiple": 16,
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "rms_norm": true,
+  "ssm_cfg": {
+    "layer": "Mamba2"
+  },
+  "state_size": 128,
+  "tie_embeddings": false,
+  "tie_word_embeddings": false,
+  "time_step_floor": 0.0001,
+  "time_step_limit": [
+    0.0,
+    Infinity
+  ],
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "vocab_size": 4096
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb1c8cd8038c8984637000bea3a135b68b9e9ce97cb7f3bd6fedc24d4888cb9
+size 2149753112

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a959515df98572b9f6666e1193becf1b94247b43f287a5c95c0ed7e67769da
+size 5304