Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

calibrate.config.py/config.orig.py

@@ -0,0 +1,33 @@
+from datetime import datetime
+from pathlib import Path
+
+def config():
+    LANG = "sum_cs_en_pl_sk"
+    LANG_SHORT = "sum_cs_en_pl_sk"
+    
+    DATE = "20230801"
+    WIKI_ROOT = f"/mnt/data/factcheck/wiki/{LANG_SHORT}/{DATE}"
+    QACG_ROOT = f"{WIKI_ROOT}/qacg"
+
+    NLI_DIR = Path("nli")
+    NLI_ROOT = Path(QACG_ROOT, NLI_DIR)
+
+    MODEL_ROOT = "/home/drchajan/devel/python/FC/Zero-shot-Fact-Verification/experiments/nli/"
+    MODEL_NAME = Path(MODEL_ROOT, "deepset/xlm-roberta-large-squad2_sum_cs_en_pl_sk-20230801_balanced_lr1e-6/checkpoint-321184")
+    MAX_LENGTH = 512
+
+    DATESTR = datetime.now().strftime("%y%m%d_%H%M%S")
+    NOTE = f"Calibrates sum language NLI model."
+
+    return {
+        "lang": LANG,
+        "lang_short": LANG_SHORT,
+        "wiki_root": WIKI_ROOT,
+        "nli_root": NLI_ROOT,
+        "model_name": MODEL_NAME,
+        "max_length": MAX_LENGTH,
+        "epochs": 50,
+        "split": str(Path(NLI_ROOT, "dev_balanced.jsonl")),
+        "note": NOTE,
+        "date": DATESTR,
+    }

calibrate.config.py/config.py

@@ -0,0 +1,10 @@
+{  'lang': 'sum_cs_en_pl_sk',
+   'lang_short': 'sum_cs_en_pl_sk',
+   'wiki_root': '/mnt/data/factcheck/wiki/sum_cs_en_pl_sk/20230801',
+   'nli_root': PosixPath('/mnt/data/factcheck/wiki/sum_cs_en_pl_sk/20230801/qacg/nli'),
+   'model_name': PosixPath('/home/drchajan/devel/python/FC/Zero-shot-Fact-Verification/experiments/nli/deepset/xlm-roberta-large-squad2_sum_cs_en_pl_sk-20230801_balanced_lr1e-6/checkpoint-321184'),
+   'max_length': 512,
+   'epochs': 50,
+   'split': '/mnt/data/factcheck/wiki/sum_cs_en_pl_sk/20230801/qacg/nli/dev_balanced.jsonl',
+   'note': 'Calibrates sum language NLI model.',
+   'date': '230925_180021'}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "/home/drchajan/devel/python/FC/Zero-shot-Fact-Verification/experiments/nli/deepset/xlm-roberta-large-squad2_sum_cs_en_pl_sk-20230801_balanced_lr1e-6/checkpoint-321184",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "text-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "n",
+    "1": "r",
+    "2": "s"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "n": 0,
+    "r": 1,
+    "s": 2
+  },
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "name": "XLMRoberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659cb3be4b4aa1c00ea91f88a6aa724b325a698cc24b0819283e8f3a6f2cb8b5
+size 2239709617

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca5f734b9407eb910ec87ecf2a0325a7c5c3436836ba12c600b0ce787b8c3a6
+size 17082983

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "full_tokenizer_file": null,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}