Initial commit : RoBERta-base HumAb VL model

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- roberta
+- masked-language-modeling
+- antibody
+- humanization
+- vl
+- light chain
+- OAS
+- protein
+- biology
+license: mit
+base_model:
+- FacebookAI/roberta-base
+pipeline_tag: fill-mask
+---
+
+# RoBERTa Base HumAb VL Model
+
+This is a RoBERTa model trained from scratch for antibody humanization of Variable Light (VL) chain sequences using Masked Language Modeling (MLM).
+
+## Model Description
+
+This model is trained on antibody light chain sequences (variable region) for humanization tasks. It can be used for antibody sequence analysis, humanization, and understanding of VL chain patterns.
+
+## Usage
+
+```python
+from transformers import RobertaTokenizer, RobertaForMaskedLM
+
+# Load tokenizer and model from Hugging Face
+tokenizer = RobertaTokenizer.from_pretrained("hemantn/roberta-base-humAb-vl")
+model = RobertaForMaskedLM.from_pretrained("hemantn/roberta-base-humAb-vl")
+```
+
+## Model Details
+
+### Architecture
+- **Model**: RoBERTa (trained from scratch)
+- **Architecture**: RobertaForMaskedLM
+- **Model Type**: Masked Language Model for antibody sequences
+
+### Specifications
+- **Hidden Size**: 768
+- **Number of Layers**: 12
+- **Number of Attention Heads**: 12
+- **Intermediate Size**: 3072
+- **Max Position Embeddings**: 145
+- **Vocabulary Size**: 25 tokens
+- **Model Size**: ~164 MB

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 24,
+  "max_position_embeddings": 145,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "sep_token_id": 2,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 1,
+  "unk_token_id": 3,
+  "use_cache": true,
+  "vocab_size": 25
+}

merges.txt

@@ -0,0 +1 @@
+#version: 0.2

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7a837feae67fc72309c1b39f98f4772215b63107b07edbfbdf51a94d28312a
+size 171621532

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad107891ea4c5fbaeb19e707214f897d2fff199f4c2bd32bf151abfd74eaab1
+size 6776

vocab.json

@@ -0,0 +1,27 @@
+{
+  "</s>": 2,
+  "<mask>": 24,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3,
+  "A": 4,
+  "C": 5,
+  "D": 6,
+  "E": 7,
+  "F": 8,
+  "G": 9,
+  "H": 10,
+  "I": 11,
+  "K": 12,
+  "L": 13,
+  "M": 14,
+  "N": 15,
+  "P": 16,
+  "Q": 17,
+  "R": 18,
+  "S": 19,
+  "T": 20,
+  "V": 21,
+  "W": 22,
+  "Y": 23
+}