Upload MolCrawl compounds GPT-2 small model

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "model_type": "gpt2",
+  "vocab_size": 612,
+  "n_positions": 1024,
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_layer": 12,
+  "n_head": 12,
+  "n_inner": 3072,
+  "activation_function": "gelu_new",
+  "resid_pdrop": 0.0,
+  "embd_pdrop": 0.0,
+  "attn_pdrop": 0.0,
+  "layer_norm_epsilon": 1e-05,
+  "initializer_range": 0.02,
+  "use_cache": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.0.0",
+  "_name_or_path": "riken-gpt2",
+  "_riken_model_args": {
+    "n_layer": 12,
+    "n_head": 12,
+    "n_embd": 768,
+    "block_size": 1024,
+    "bias": false,
+    "vocab_size": 612,
+    "dropout": 0.0
+  },
+  "_riken_bias": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d56393096242d67d18968e31823147a9494aed1d383b2dce0535ccbbcf5ff55
+size 344866536

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "SmilesTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.json

@@ -0,0 +1,17 @@
+{
+  "iteration": 6000,
+  "best_val_loss": 0.030465448275208473,
+  "early_stopping_counter": 1,
+  "learning_rate": 6e-06,
+  "batch_size": 8,
+  "block_size": 1024,
+  "model_args": {
+    "n_layer": 12,
+    "n_head": 12,
+    "n_embd": 768,
+    "block_size": 1024,
+    "bias": false,
+    "vocab_size": 612,
+    "dropout": 0.0
+  }
+}