Update README.md

README.md

@@ -32,23 +32,23 @@ nor has it been tested on other downstream tasks.
 TODO: get model architecture like on the model card of the previous model
 
 Full architecture:
-`[
-  {
-    "idx": 0,
-    "name": "0",
-    "path": "0_ASMTransformerModule",
-    "type": "asmtransformers.models.asmsentencebert.ASMTransformerModule"
-  },
-  {
-    "idx": 1,
-    "name": "1",
-    "path": "1_Pooling",
-    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
-  }
-]`
+  [
+    {
+      "idx": 0,
+      "name": "0",
+      "path": "0_ASMTransformerModule",
+      "type": "asmtransformers.models.asmsentencebert.ASMTransformerModule"
+    },
+    {
+      "idx": 1,
+      "name": "1",
+      "path": "1_Pooling",
+      "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+    }
+  ]
 
 Parameters used: 
-  `{
+  {
     "architectures": [
       "BertForMaskedLM"
     ],
@@ -71,18 +71,18 @@ Parameters used:
     "type_vocab_size": 2,
     "use_cache": true,
     "vocab_size": 6161
-  }`
+  }
 
 Preraining parameters used: 
-`{
-  "epochs"=19, 
-  "eval_steps"=10000, 
-  "batch_size"=512, 
-  "gradient_accumulation_steps"=1, 
-  "mlm_prob"=0.4, 
-  "bf16"=True, 
-  "tf32"=True
-  }`
+  {
+    "epochs"=19, 
+    "eval_steps"=10000, 
+    "batch_size"=512, 
+    "gradient_accumulation_steps"=1, 
+    "mlm_prob"=0.4, 
+    "bf16"=True, 
+    "tf32"=True
+  }
 
 Note that during pretraining, the --mlm-prob parameter has been set to 0.4, in accordance to [paper](INSERT LINK)