Duplicate from julien-c/EsperBERTo-small-pos

Co-authored-by: Julien Chaumond <[email protected]>

.gitattributes

@@ -0,0 +1,10 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,43 @@
+---
+language: eo
+thumbnail: https://huggingface.co/blog/assets/01_how-to-train/EsperBERTo-thumbnail-v2.png
+widget:
+- text: Mi estas viro kej estas tago varma.
+duplicated_from: julien-c/EsperBERTo-small-pos
+---
+
+# EsperBERTo: RoBERTa-like Language model trained on Esperanto
+
+**Companion model to blog post https://huggingface.co/blog/how-to-train** 🔥
+
+## Training Details
+
+- current checkpoint: 566000
+- machine name: `galinette`
+
+
+![](https://huggingface.co/blog/assets/01_how-to-train/EsperBERTo-thumbnail-v2.png)
+
+## Example pipeline
+
+```python
+from transformers import TokenClassificationPipeline, pipeline
+
+
+MODEL_PATH = "./models/EsperBERTo-small-pos/"
+
+nlp = pipeline(
+    "ner",
+    model=MODEL_PATH,
+    tokenizer=MODEL_PATH,
+)
+# or instantiate a TokenClassificationPipeline directly.
+
+nlp("Mi estas viro kej estas tago varma.")
+
+# {'entity': 'PRON', 'score': 0.9979867339134216, 'word': ' Mi'}
+# {'entity': 'VERB', 'score': 0.9683094620704651, 'word': ' estas'}
+# {'entity': 'VERB', 'score': 0.9797462821006775, 'word': ' estas'}
+# {'entity': 'NOUN', 'score': 0.8509314060211182, 'word': ' tago'}
+# {'entity': 'ADJ', 'score': 0.9996201395988464, 'word': ' varma'}
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "_num_labels": 6,
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "NOUN",
+    "2": "ADJ",
+    "3": "ADV",
+    "4": "VERB",
+    "5": "PRON"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 2,
+    "ADV": 3,
+    "NOUN": 1,
+    "O": 0,
+    "PRON": 5,
+    "VERB": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "output_past": true,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 52000
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc59c5b16cfe0888c80bc8e4ef17b5feed02dacd32a22354abf860bf17cba85e
+size 331463343

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91858d873cf0e9c58ae63cdc1b8f50586f9a74078b1e0134f026d7b015b9065b
+size 333834486

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562055090b2745c85f0e74162f6283a22f3c79e005870ae9d8e4504afdfa035d
+size 331605810

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283f2b0300cc6e49c2b8dda8c10364c7c274df4e6e4470708ea957a7e1e88b47
+size 83499694

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3f102b0ff6cc1bc649beab8e46fcaa21193e3aabfd427f229d61070615a385
+size 333848590

quant_config.json

@@ -0,0 +1,36 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "ConstantOfShape",
+                "Sqrt",
+                "Slice",
+                "Pow",
+                "Transpose",
+                "Where",
+                "Softmax",
+                "Gather",
+                "MatMul",
+                "Erf",
+                "Mul",
+                "Cast",
+                "Expand",
+                "Div",
+                "Add",
+                "Constant",
+                "Sub",
+                "Not",
+                "Reshape",
+                "ReduceMean",
+                "Unsqueeze",
+                "Shape",
+                "Concat",
+                "CumSum",
+                "Equal"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}