Upload model

README.md

@@ -1,3 +1,24 @@
----
-license: apache-2.0
----
+## `semanlink_all_mpnet_base_v2`
+
+This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+`semanlink_all_mpnet_base_v2` has been fine-tuned on the knowledge graph [Semanlink](http://www.semanlink.net/sl/home?lang=fr) via the library [MKB](https://github.com/raphaelsty/mkb) on the link-prediction task. The model is dedicated to the representation of both technical and generic terminology in machine learning, NLP, news.
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have sentence-transformers installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["Machine Learning", "Geoffrey Hinton"]
+
+model = SentenceTransformer('raphaelsty/semanlink_all_mpnet_base_v2')
+embeddings = model.encode(sentences)
+print(embeddings)
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "vocab_size": 30527
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "sentence-transformers/all-mpnet-base-v2", "tokenizer_class": "MPNetTokenizer"}