Fitted

config.json

@@ -1,33 +1,28 @@
 {
   "architectures": [
-    "MambaForCausalLM"
+    "DebertaV2ForMaskedLM"
   ],
-  "bos_token_id": 2,
-  "conv_kernel": 4,
-  "eos_token_id": 3,
-  "expand": 1,
-  "hidden_act": "silu",
-  "hidden_size": 256,
-  "initializer_range": 0.1,
-  "intermediate_size": 128,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "mamba",
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 256,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "num_attention_heads": 2,
   "num_hidden_layers": 8,
   "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": 16,
-  "time_step_scale": 1.0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 128,
+  "pos_att_type": null,
+  "position_biased_input": true,
+  "relative_attention": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
-  "use_bias": false,
-  "use_cache": true,
-  "use_conv_bias": true,
-  "use_mambapy": true,
-  "vocab_size": 32768
+  "transformers_version": "4.46.0",
+  "type_vocab_size": 0,
+  "vocab_size": 64000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d33fc899d5d2281ee1507404c7d2f6a727634bad55e476910f4d7f9b85bc0e
-size 37074304
+oid sha256:febeae424c9146aab624570729b9ac8ff061d492dc36e430296e0968b09ec8a0
+size 39584240

special_tokens_map.json

@@ -1,8 +1,51 @@
 {
-  "bos_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb22f68b798542aebc9821a20566d634e4e8136d122e21c6c3f022ff4c75e4c
+size 1698052

tokenizer_config.json

@@ -11,7 +11,7 @@
     "1": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -43,11 +43,15 @@
   },
   "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "tokenizer_class": "PreTrainedTokenizerFast",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
   "unk_token": "[UNK]"
 }