Checkpoint 390500

config.json

@@ -0,0 +1,45 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_layers": [
+    "global",
+    "global",
+    "global",
+    "global",
+    "global",
+    "global"
+  ],
+  "attention_types": [
+    [
+      [
+        "global"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 1024,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 6,
+  "resid_dropout": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.5.1",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc6b9177a99ec20e2a8d9b629ba10496c27c3376a85ac11f23d9b25e651c7da
+size 333916933

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|unknown|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "max_len": 1024, "bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "special_tokens_map_file": "special_tokens_map.json", "full_tokenizer_file": null}