First model version

README.md

@@ -0,0 +1,5 @@
+Base model: [gpt2-xl](https://huggingface.co/gpt2-xl)
+
+Domain-adapted for dialogue response and narrative generation on a [narrative-aligned variant](https://github.com/AbrahamSanders/gutenberg-dialog#download-narrative-aligned-datasets) of the [Gutenberg Dialogue Dataset (Csaky & Recski, 2021)](https://aclanthology.org/2021.eacl-main.11.pdf)
+
+Fine-tuned for dialogue response generation on [Persuasion For Good (Wang et al., 2019)](https://aclanthology.org/P19-1566.pdf) ([dataset](https://gitlab.com/ucdavisnlp/persuasionforgood))

added_tokens.json

@@ -0,0 +1 @@
+{"<|pad|>": 50257, "<|dialog|>": 50259, "<|narrative|>": 50258}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "output_gutenberg/checkpoint-400000-nockpt",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.4.2",
+  "use_cache": true,
+  "vocab_size": 50260
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a906299d4ece61fd389cba39e07259d98bc5cd582f3529aa36d6f1c39c2b0f
+size 6281058871

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|pad|>", "additional_special_tokens": ["<|narrative|>", "<|dialog|>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "output_gutenberg/checkpoint-400000-nockpt", "errors": "replace"}