Authorial language model for Sophocles

README.md

@@ -0,0 +1,56 @@
+---
+language:
+- grc
+license: other
+base_model: allenai/OLMo-1B-hf
+tags:
+- ancient-greek
+- authorship-attribution
+- authorial-language-model
+---
+
+# Authorial language model: Sophocles (Sphragis sentences)
+
+One of 28 authorial language models (ALMs) for the [Sphragis](https://huggingface.co/datasets/Urdatorn/sphragis)
+Ancient Greek authorship-attribution benchmark, following Huang, Murakami and
+Grieve (2025), "Attributing authorship via the perplexity of authorial language
+models", PLoS ONE 20(7): e0327081. Each model is a full further-pretraining of
+[`allenai/OLMo-1B-hf`](https://huggingface.co/allenai/OLMo-1B-hf) (revision `aee7752d9c08ee4775e9b0091426d8410e8f6a89`) on
+**one author's training rows only**; a row is attributed to whichever of the
+28 models finds it least surprising.
+
+This model was trained on **Sophocles**: 3,100 rows, 141,896 scored
+tokens from the `sentence_1` training split. Its base model and the number of
+epochs were both chosen by coordinate ascent on validation attribution, so a
+model here may start from the vanilla OLMo-1B or from the Greek-adapted one.
+
+## Training
+
+| | |
+|---|---|
+| Objective | causal LM on `<\|endoftext\|> sentence <\|endoftext\|>`, one sentence per sequence |
+| Selection | validation attribution macro-F1 over all 28 models |
+| Epochs | 2 |
+| Learning rate | 5e-05, constant after 25 warmup steps |
+| Effective batch | 16 sentences |
+| Precision | fp32 master weights, bf16 compute, FSDP full shard on 2x GH200 |
+| Weights | bf16 |
+
+Unlike Huang and colleagues' fixed 100 epochs, training length here is chosen by
+held-out evidence -- and on attribution itself rather than on this author's own
+perplexity, because what attribution needs is not how well a model fits its
+author but how much better it fits than the others.
+
+## Scoring
+
+Score a sentence exactly as it was trained, and compare the per-token negative
+log-likelihood against the other sixteen models. Together the twenty-eight models reach 62.36 test macro-F1 on sentence_1, 86.84 on sentence_5, 89.53 on sentence_10 and 92.44 on sentence_50.
+
+Training, scoring, and attribution code:
+[`Urdatorn/sphragis_models`](https://github.com/Urdatorn/sphragis_models).
+
+## Licence and provenance
+
+The base model is Apache-2.0. The training text comes from the benchmark, whose
+sources carry mixed licences including CC BY-NC-SA material, so this derived
+model is released as `other`: see the dataset's `LICENSES.md` before reuse.

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "OlmoForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "clip_qkv": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 50279,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 2048,
+  "model_type": "olmo",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 0,
+  "pad_token_id": 1,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d494cc702c69cca3166b57e3542694ac85e78bf969c072b45f31284c546cd6f
+size 2353541856

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": null
+}