Upload folder using huggingface_hub

README.md

@@ -1,3 +1,30 @@
----
-license: bsd-3-clause
----
+---
+pretty_name: p-IgGen
+library_name: transformers
+tags: [science, antibodies, protein,drug discovery]
+---
+
+# Model Card for Model ID
+
+Auto-regressive protein language model for paired antibody library generation.
+
+Pretrained on unpaired heavy and light chain sequences from the Observed Antibody Space (OAS), and finetuned on paired sequences.
+
+## Getting Started?
+
+This model was featured in the Hugging Face blog ***How to Train an Antibody Developability Model*** (found here: https://huggingface.co/blog/ginkgo-datapoints/making-antibody-embeddings-and-predictions). Sample code on how to get started using this model can be found in the blog.
+
+## Model Details
+
+### Model Description
+
+
+- **Funded by:** EPSRC, AstraZeneca
+- **License:**  BSD-3-Clause license
+
+### Model Sources
+
+<!-- Provide the basic links for the model. -->
+Note: This is a duplicate of Ollie Turnbull's model repo, found here: https://huggingface.co/ollieturnbull/p-IgGen
+- **Repository:** https://github.com/OliverT1/p-IgGen
+- **Paper:** https://academic.oup.com/bioinformatics/article/40/11/btae659/7888884

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": ".",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 400,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 26
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fac8e89ae5abb432e29c3af2ca5176da6b6bbeef64ea6847bd51393180918bd
+size 88395416

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,73 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<PAD>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "vocab": {
+      "<PAD>": 0,
+      "A": 1,
+      "R": 2,
+      "N": 3,
+      "D": 4,
+      "B": 5,
+      "C": 6,
+      "E": 7,
+      "Q": 8,
+      "Z": 9,
+      "G": 10,
+      "H": 11,
+      "I": 12,
+      "L": 13,
+      "K": 14,
+      "M": 15,
+      "F": 16,
+      "P": 17,
+      "S": 18,
+      "T": 19,
+      "W": 20,
+      "Y": 21,
+      "V": 22,
+      "1": 23,
+      "2": 24,
+      "3": 25
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 512,
+  "pad_token": "<PAD>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}