update model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

code/inference.py

@@ -0,0 +1,25 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: MIT-0
+
+from transformers import EsmForSequenceClassification, AutoTokenizer
+import torch
+
+
+def model_fn(model_dir):
+    model = EsmForSequenceClassification.from_pretrained(model_dir, device_map="auto")
+    tokenizer = AutoTokenizer.from_pretrained(model_dir)
+
+    return model, tokenizer
+
+
+def predict_fn(data, model_and_tokenizer):
+    model, tokenizer = model_and_tokenizer
+    model.eval()
+    inputs = data.pop("inputs", data)
+    encoding = tokenizer(inputs, return_tensors="pt")
+    encoding = {k: v.to(model.device) for k, v in encoding.items()}
+    results = model(**encoding)
+    sigmoid = torch.nn.Sigmoid()
+    probs = sigmoid(results.logits)
+    probs = probs.cpu()
+    return {"membrane_probability": probs[0][1].item()}

code/requirements.txt

@@ -0,0 +1,9 @@
+accelerate==0.24.1
+bitsandbytes==0.41.1
+datasets==2.14.6
+evaluate==0.4.1
+nvidia-ml-py3==7.352.0
+peft==0.5.0
+scikit-learn==1.3.2
+transformers==4.34.1
+torchinfo==1.8.0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c4958cbcc3232d64235b1a6abcec5d26396b74e0d74bb3794a3e0ec359d263
+oid sha256:0ad09ac9c1d4555f9b60afa48cdfb79e0145ea513a442445038b397f65a817d6
 size 1304903737

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "EsmTokenizer",
+  "unk_token": "<unk>"
+}

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>