Upload 12 files

BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext/config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "model_type": "bert",
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext/tokenizer_config.json

@@ -0,0 +1,3 @@
+{
+  "do_lower_case": true
+}

CLAProt_35M_UniRef50.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6e1e6d3be3da196e80e7dc5447c470badf903a5df3e53de27bbe04bc09c76b
+size 711044942

esm2_t12_35M_UR50D/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "EsmForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 480,
+  "initializer_range": 0.02,
+  "intermediate_size": 1920,
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0.dev0",
+  "use_cache": true,
+  "vocab_size": 33
+}

esm2_t12_35M_UR50D/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

esm2_t12_35M_UR50D/tokenizer_config.json

@@ -0,0 +1,3 @@
+{
+  "tokenizer_class": "EsmTokenizer"
+}

esm2_t12_35M_UR50D/vocab.txt

@@ -0,0 +1,33 @@
+<cls>
+<pad>
+<eos>
+<unk>
+L
+A
+G
+V
+S
+E
+R
+T
+I
+D
+P
+K
+Q
+N
+F
+Y
+M
+H
+W
+C
+X
+B
+U
+Z
+O
+.
+-
+<null_1>
+<mask>

foldseek_t12_35M/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "EsmForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 480,
+  "initializer_range": 0.02,
+  "intermediate_size": 1920,
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 4,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0.dev0",
+  "use_cache": true,
+  "vocab_size": 26
+}

foldseek_t12_35M/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

foldseek_t12_35M/tokenizer_config.json

@@ -0,0 +1,3 @@
+{
+  "tokenizer_class": "EsmTokenizer"
+}

foldseek_t12_35M/vocab.txt

@@ -0,0 +1,26 @@
+<cls>
+<pad>
+<eos>
+<unk>
+<mask>
+p
+y
+n
+w
+r
+q
+h
+g
+d
+l
+v
+t
+m
+f
+s
+a
+e
+i
+k
+c
+#