Initial upload

README.md

@@ -0,0 +1,10 @@
+# fdh-wikibio
+
+Model used to prepare Biography Generator for EPFL Foundations of Digital Humanities course.
+
+## Project description
+Please read our report on FDH page: http://fdh.epfl.ch/index.php/WikiBio
+
+## Project result
+You're invited to read through our generated biographies!
+https://wikibio.mbien.pl/

added_tokens.json

@@ -0,0 +1 @@
+{"<|start|>": 50257, "<|description|>": 50258, "<|summary|>": 50259, "<|professions|>": 50260, "<|birth|>": 50261, "<|death|>": 50262, "<|section|>": 50263, "<|end|>": 50264, "<|pad|>": 50265}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "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,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": 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
+    }
+  },
+  "vocab_size": 50266
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988edc0425e479f89d381bad9b6608aa4a1027324b4b1e37e16295998b1c23e4
+size 1444622975

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|pad|>", "additional_special_tokens": ["<|start|>", "<|description|>", "<|summary|>", "<|professions|>", "<|birth|>", "<|death|>", "<|section|>", "<|end|>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "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, "name_or_path": "gpt2"}