Upload MolCrawl genome sequence GPT-2 medium model

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "model_type": "gpt2",
+  "vocab_size": 4096,
+  "n_positions": 1024,
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_layer": 24,
+  "n_head": 16,
+  "n_inner": 4096,
+  "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": 24,
+    "n_head": 16,
+    "n_embd": 1024,
+    "block_size": 1024,
+    "bias": false,
+    "vocab_size": 4096,
+    "dropout": 0.0
+  },
+  "_riken_bias": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61893b7979c89df25a7b2a0c8e746f9987b32d83c524700013a283c839e8ba80
+size 1229180911

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6ffbcfbd4fcbccd53551b83eec5ccbf70bb09d5508826a481f5d0286e755d6
+size 75663

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

training_args.json

@@ -0,0 +1,17 @@
+{
+  "iteration": 50000,
+  "best_val_loss": 5.49131965637207,
+  "early_stopping_counter": 10,
+  "learning_rate": 6e-06,
+  "batch_size": 12,
+  "block_size": 1024,
+  "model_args": {
+    "n_layer": 24,
+    "n_head": 16,
+    "n_embd": 1024,
+    "block_size": 1024,
+    "bias": false,
+    "vocab_size": 4096,
+    "dropout": 0.0
+  }
+}