Upload 4 files

README.md

@@ -1,3 +1,20 @@
----
-license: mit
----
+# ProtAlbert
+
+```python
+from transformers import AutoModel, AlbertTokenizer, pipeline
+import re
+
+tokenizer = AlbertTokenizer.from_pretrained("Rostlab/prot_albert", do_lower_case=False)
+
+model = AutoModel.from_pretrained("Rostlab/prot_albert")
+
+fe = pipeline('feature-extraction', model=model, tokenizer=tokenizer, device=0)
+
+sequences_Example = ["A E T C Z A O", "S K T Z P"]
+
+sequences_Example = [re.sub(r"[UZOB]", "X", sequence) for sequence in sequences_Example]
+
+embedding = fe(sequences_Example)
+
+print(embedding)
+```

config.json

@@ -0,0 +1,21 @@
+{
+  "attention_probs_dropout_prob": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "embedding_size": 128,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 40000,
+  "num_attention_heads": 64,
+  "num_hidden_layers": 12,
+  "num_hidden_groups": 1,
+  "net_structure_type": 0,
+  "layers_to_keep": [],
+  "gap_size": 0,
+  "num_memory_blocks": 0,
+  "inner_group_num": 1,
+  "down_scale_factor": 1,
+  "type_vocab_size": 2,
+  "vocab_size": 34
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f616acbd5007236453cef55029264af6da30d8f4491a4e5f63641055e53d2b6
+size 897396780

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2bd947f6400f10d02c65a9ca396e607bf89e076cfd3f9775e9ef053539998d9
+size 238187