Upload 14 files

.gitattributes

@@ -1,35 +1,21 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz 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
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+flax_model.msgpack filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/29/93/29936a7b8af6bfb56f24e9a162e586c784b05997fdb6a2fdfca3d69bf0368feb filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/6e/af/6eaf3508e4f24b3942477ea5d3b65c2a5ea3e81d2932c885c8644f43cbfc8b53 filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -1,3 +1,107 @@
 ---
+pipeline_tag: sentence-similarity
 license: apache-2.0
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
 ---
+
+# sentence-transformers/stsb-roberta-base-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('sentence-transformers/stsb-roberta-base-v2')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/stsb-roberta-base-v2')
+model = AutoModel.from_pretrained('sentence-transformers/stsb-roberta-base-v2')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, max pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/stsb-roberta-base-v2)
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+This model was trained by [sentence-transformers](https://www.sbert.net/). 
+        
+If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
+```bibtex 
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "http://arxiv.org/abs/1908.10084",
+}
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "old_models/stsb-roberta-base-v2/0_Transformer",
+  "architectures": [
+    "HFAdaptedRoBERTaHeadless"
+  ],
+  "auto_map": {
+    "AutoConfig": "modeling_roberta.HFAdaptedRoBERTaConfig",
+    "AutoModel": "modeling_roberta.HFAdaptedRoBERTaHeadless"
+  },
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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": "roberta-custom",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

modeling_roberta.py

@@ -0,0 +1,188 @@
+from typing import Optional, Tuple
+
+import torch
+import torch.nn as nn
+from transformers import PretrainedConfig
+from transformers.modeling_outputs import BaseModelOutputWithPastAndCrossAttentions
+
+from fms.models.hf.lm_head_mixins import (
+    MaskedLMHeadMixin,
+    SequenceClassificationLMHeadMixin,
+)
+from fms.models.hf.modeling_hf_adapter import HFEncoder, HFEncoderModelArchitecture
+from fms.models.roberta import RoBERTa, RoBERTaConfig, RoBERTaHeadless
+
+
+class HFAdaptedRoBERTaConfig(PretrainedConfig):
+    model_type = "hf_adapted_roberta"
+
+    attribute_map = {
+        "vocab_size": "src_vocab_size",
+        "hidden_size": "emb_dim",
+        "num_attention_heads": "nheads",
+        "num_hidden_layers": "nlayers",
+        "tie_word_embeddings": "tie_heads",
+    }
+
+    def __init__(
+        self,
+        src_vocab_size=None,
+        emb_dim=None,
+        nheads=12,
+        nlayers=12,
+        max_pos=512,
+        pad_token_id=1,
+        hidden_grow_factor=4,
+        activation_fn="gelu",
+        classifier_activation_fn="tanh",
+        p_dropout=0.1,
+        classifier_dropout=0.1,
+        use_cache=True,
+        num_labels=1,
+        norm_eps=1e-12,
+        tie_heads=False,
+        **kwargs,
+    ):
+        self.src_vocab_size = src_vocab_size
+        self.emb_dim = emb_dim
+        self.nheads = nheads
+        self.nlayers = nlayers
+        self.max_pos = max_pos
+        self.hidden_grow_factor = hidden_grow_factor
+        if activation_fn.lower() not in ["gelu", "relu", "mish", "swish"]:
+            raise ValueError(
+                "activation function must be one of gelu, relu, mish, swish"
+            )
+        self.activation_fn = activation_fn
+        self.p_dropout = p_dropout
+        self.classifier_dropout = classifier_dropout
+        self.use_cache = use_cache
+        self.norm_eps = norm_eps
+        self.classifier_activation_fn = classifier_activation_fn
+        self.tie_heads = tie_heads
+        super().__init__(
+            pad_token_id=pad_token_id,
+            num_labels=num_labels,
+            tie_word_embeddings=kwargs.pop("tie_word_embeddings", tie_heads),
+            **kwargs,
+        )
+
+    @classmethod
+    def from_pretrained(
+        cls, pretrained_model_name_or_path, **kwargs
+    ) -> "PretrainedConfig":
+        config_dict, kwargs = cls.get_config_dict(
+            pretrained_model_name_or_path, **kwargs
+        )
+
+        return cls.from_dict(config_dict, **kwargs)
+
+    @classmethod
+    def from_fms_config(cls, config: RoBERTaConfig, **hf_kwargs):
+        config_dict = config.as_dict()
+        config_dict["pad_token_id"] = config_dict.pop("pad_id")
+        return cls.from_dict(config_dict, **hf_kwargs)
+
+
+class HFAdaptedRoBERTaEncoder(HFEncoder):
+    """Adapter for the Roberta Encoder"""
+
+    def __init__(self, model: RoBERTaHeadless, config: PretrainedConfig):
+        super().__init__(model, config, attention_mask_dim=3)
+
+    def _adapt(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        head_mask: Optional[torch.FloatTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        *args,
+        **kwargs,
+    ) -> BaseModelOutputWithPastAndCrossAttentions:
+        return BaseModelOutputWithPastAndCrossAttentions(
+            last_hidden_state=self.model(
+                x=input_ids, mask=attention_mask, position_ids=position_ids
+            )
+        )
+
+
+class HFAdaptedRoBERTaHeadless(HFEncoderModelArchitecture):
+    # attributes required by HF
+    config_class = HFAdaptedRoBERTaConfig
+    base_model_prefix = "hf_adapted_roberta"
+
+    def __init__(
+        self,
+        config: PretrainedConfig,
+        encoder: Optional[RoBERTaHeadless] = None,
+        embedding: Optional[nn.Module] = None,
+        *args,
+        **kwargs,
+    ):
+        # in the case we have not yet received the encoder/decoder/embedding, initialize it here
+        if encoder is None or embedding is None:
+            params = config.to_dict()
+            model = RoBERTa(pad_id=params.pop("pad_token_id"), **params)
+            encoder = model.base_model if encoder is None else encoder
+            embedding = model.base_model.embedding if embedding is None else embedding
+
+        # these are now huggingface compatible
+        encoder = HFAdaptedRoBERTaEncoder(encoder, config)
+        super().__init__(encoder, embedding, config, *args, **kwargs)
+
+
+class HFAdaptedRoBERTaForMaskedLM(MaskedLMHeadMixin, HFAdaptedRoBERTaHeadless):
+    def __init__(self, config: HFAdaptedRoBERTaConfig, *args, **kwargs):
+        super().__init__(
+            config=config,
+            activation_fn=config.activation_fn,
+            norm_eps=config.norm_eps,
+            *args,
+            **kwargs,
+        )
+
+    @classmethod
+    def _hf_model_from_fms(
+        cls, model: RoBERTa, config: HFAdaptedRoBERTaConfig
+    ) -> "HFAdaptedRoBERTaForMaskedLM":
+        return cls(
+            config=config,
+            encoder=model.base_model,
+            embedding=model.base_model.embedding,
+            lm_head=model.classification_head,
+        )
+
+
+class HFAdaptedRoBERTaForSequenceClassification(
+    SequenceClassificationLMHeadMixin, HFAdaptedRoBERTaHeadless
+):
+    def __init__(
+        self,
+        config: HFAdaptedRoBERTaConfig,
+        encoder: Optional[nn.Module] = None,
+        embedding: Optional[nn.Module] = None,
+        *args,
+        **kwargs,
+    ):
+        super().__init__(
+            config=config,
+            classifier_activation_fn=config.classifier_activation_fn,
+            classifier_dropout=config.classifier_dropout,
+            encoder=encoder,
+            embedding=embedding,
+            *args,
+            **kwargs,
+        )
+
+    @classmethod
+    def _hf_model_from_fms(
+        cls, model: RoBERTa, config: HFAdaptedRoBERTaConfig
+    ) -> "HFAdaptedRoBERTaForSequenceClassification":
+        return cls(
+            config=config,
+            encoder=model.base_model,
+            embedding=model.base_model.embedding,
+        )

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417c0e9ea35a21ead76cb2fe422b51ff7fbd2a206654754753ddc6b27a17ba7c
+size 498661169

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 75,
+  "do_lower_case": false
+}

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 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "old_models/stsb-roberta-base-v2/0_Transformer"}