Duplicate from facebook/esmfold_v1

Co-authored-by: Matthew Carrigan <Rocketknight1@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,33 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,9 @@
+---
+license: mit
+---
+
+# ESMFold
+
+ESMFold is a state-of-the-art end-to-end protein folding model based on an ESM-2 backbone. It does not require any lookup or MSA step, and therefore does not require any external databases to be present in order to make predictions. As a result, inference time is very significantly faster than AlphaFold2. For details on the model architecture and training, please refer to the [accompanying paper](https://www.science.org/doi/10.1126/science.ade2574).
+
+If you're interested in using ESMFold in practice, please check out the associated [tutorial notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/protein_folding.ipynb).

config.json

@@ -0,0 +1,103 @@
+{
+  "architectures": [
+    "EsmForProteinFolding"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": {
+    "bypass_lm": false,
+    "embed_aa": true,
+    "esm_ablate_pairwise": false,
+    "esm_ablate_sequence": false,
+    "esm_input_dropout": 0,
+    "esm_type": "esm2_3B",
+    "fp16_esm": false,
+    "lddt_head_hid_dim": 128,
+    "trunk": {
+      "chunk_size": null,
+      "cpu_grad_checkpoint": false,
+      "dropout": 0,
+      "layer_drop": 0,
+      "max_recycles": 4,
+      "num_blocks": 48,
+      "pairwise_head_width": 32,
+      "pairwise_state_dim": 128,
+      "position_bins": 32,
+      "sequence_head_width": 32,
+      "sequence_state_dim": 1024,
+      "structure_module": {
+        "dropout_rate": 0.1,
+        "epsilon": 1e-08,
+        "inf": 100000.0,
+        "ipa_dim": 16,
+        "num_angles": 7,
+        "num_blocks": 8,
+        "num_heads_ipa": 12,
+        "num_qk_points": 4,
+        "num_resnet_blocks": 2,
+        "num_transition_layers": 1,
+        "num_v_points": 8,
+        "pairwise_dim": 128,
+        "resnet_dim": 128,
+        "sequence_dim": 384,
+        "trans_scale_factor": 10
+      }
+    },
+    "use_esm_attn_map": false
+  },
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "is_folding_model": true,
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 36,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_list": [
+    "<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>"
+  ],
+  "vocab_size": 33
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee07356b125d1e3e57503c204111fd7323347fc4735d41d3caac57c2a78e116
+size 8442062570

special_tokens_map.json

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

tokenizer_config.json

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

vocab.txt

@@ -0,0 +1,26 @@
+A
+R
+N
+D
+C
+Q
+E
+G
+H
+I
+L
+K
+M
+F
+P
+S
+T
+W
+Y
+V
+X
+<pad>
+<mask>
+<cls>
+<sep>
+<eos>