Small2 but sharded.

Created to test safetensors conversion.

README.md

@@ -0,0 +1 @@
+Small change. again. again ? again.

config.json

@@ -0,0 +1,52 @@
+{
+    "_name_or_path": "Narsil/small2",
+    "_num_labels": 9,
+    "architectures": ["BertForTokenClassification"],
+    "attention_probs_dropout_prob": 0.1,
+    "classifier_dropout": null,
+    "directionality": "bidi",
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 2,
+    "id2label": {
+        "0": "O",
+        "1": "B-MISC",
+        "2": "I-MISC",
+        "3": "B-PER",
+        "4": "I-PER",
+        "5": "B-ORG",
+        "6": "I-ORG",
+        "7": "B-LOC",
+        "8": "I-LOC"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4,
+    "label2id": {
+        "B-LOC": 7,
+        "B-MISC": 1,
+        "B-ORG": 5,
+        "B-PER": 3,
+        "I-LOC": 8,
+        "I-MISC": 2,
+        "I-ORG": 6,
+        "I-PER": 4,
+        "O": 0
+    },
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "bert",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "transformers_version": "4.10.0.dev0",
+    "type_vocab_size": 2,
+    "use_cache": true,
+    "vocab_size": 28996
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f87650c29f497c39f9265f3f8d5cbff82d350d656f17f84211f604773569eb3f
+size 4907

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2c2f5f27c0ef9e57571711be399b4f6db326d559b66102a5fa9276affafb1e
+size 232747

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350be52b37c1248f4df7fc72adf5105202166780689215c2ff1269a33f2ed5ff
+size 15795

pytorch_model.bin.index.json

@@ -0,0 +1,47 @@
+{
+  "metadata": {
+    "total_size": 240732
+  },
+  "weight_map": {
+    "bert.embeddings.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.embeddings.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.embeddings.position_embeddings.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
+    "bert.embeddings.token_type_embeddings.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.embeddings.word_embeddings.weight": "pytorch_model-00002-of-00003.bin",
+    "bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.0.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "bert.encoder.layer.1.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "classifier.bias": "pytorch_model-00003-of-00003.bin",
+    "classifier.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28422e5654b34d4d92f8675c7b563e01992322451c74cefec9137084ac797766
+size 301400

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "max_len": 512, "special_tokens_map_file": "/home/nicolas/.cache/torch/transformers/7ed0658a09e4f9689057c83f8b734d0e8d739f73461c7b7d1bc403aa451e304b.275045728fbf41c11d3dae08b8742c054377e18d92cc7b72b6351152a99b64e4", "tokenizer_file": null}

unigram.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6c5a850287ee371b9c2c74ba1c9b10a85ce0436c0e53685903caa635dd2aa3
+size 146491