Update README.md

README.md

@@ -1,278 +1,39 @@
----
-language: en
-tags:
-- adverse event detection
-datasets:
-- bookcorpus
-- wikipedia
-libraries:
-- pytorch
-- transformers
-task:
-- Fill-Mask
----
-
-MAPV DeepMind leverages the metadata on top of README.md to set the tags and
-appropriate markdown for your model. This metadata are inserted using `yaml` notation. For instance,
-at the begining of your README.md adding the following, wrapped in `---` to indicate start and end of
-the metadata:
-
-
-```yaml
-language: en
-tags:
-- adverse event detection
-datasets:
-- bookcorpus
-- wikipedia
-libraries:
-- pytorch
-- transformers
-task:
-- Fill-Mask
-```
-
-Would result in adding `adverse event detection` tag and implying what `dataset` you used for training
-your model. `libraries` indicate the implementation library of your model such as pytorch. DeepMind has a set of predefined
-tasks to appropriately identify the inference pipeline for your model. Currently, only NLP inference tasks are
-supported. For instace setting the `task` to `Fill-Mask` would result in the inference widget to be set for this task.
-
-# bge-reranker-v2-m3-onnx-o4
-
-Here you are able to employ `Markdown` to describe your model.
-
-You could use references:
-
-1. [this paper on arxiv](https://arxiv.org/abs/1810.04805)
-
-Or
-
-2. Online images ![model image](https://camo.githubusercontent.com/623b4dea0b653f2ad3f36c71ebfe749a677ac0a1/68747470733a2f2f6d69726f2e6d656469756d2e636f6d2f6d61782f343030362f312a44304a31674e51663876727255704b657944387750412e706e67)
-
-
-Please use this template to describe your model. The following sections are examples of describing BERT model, one of
-the earliest transformer architectures.
-
-## Model Diagram
-
-We support [`mermaid`](https://mermaid-js.github.io/mermaid/#/) so you could describe your work using awesome `mermaid` diagrams:
-
-```mermaid
-graph TD
-    A[mymodel] -->|good data| B(awesomeness)
-```
-
-$$p(x|y) = rac{p(y|x)p(x)}{p(y)}$$
-
-## Model description
-
-BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
-was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
-publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
-was pretrained with two objectives:
-
-- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
-  the entire masked sentence through the model and has to predict the masked words. This is different from traditional
-  recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
-  GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
-  sentence.
-- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
-  they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
-  predict if the two sentences were following each other or not.
-
-This way, the model learns an inner representation of the English language that can then be used to extract features
-useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
-classifier using the features produced by the BERT model as inputs.
-
-## Intended uses & limitations
-
-You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
-be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=bert) to look for
-fine-tuned versions on a task that interests you.
-
-Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
-to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
-generation you should look at model like GPT2.
-
-### How to use
-
-You can use this model directly with a pipeline for masked language modeling:
-
-```python
->>> from transformers import pipeline
->>> unmasker = pipeline('fill-mask', model='bert-base-uncased')
->>> unmasker("Hello I'm a [MASK] model.")
-
-[{'sequence': "[CLS] hello i'm a fashion model. [SEP]",
-  'score': 0.1073106899857521,
-  'token': 4827,
-  'token_str': 'fashion'},
- {'sequence': "[CLS] hello i'm a role model. [SEP]",
-  'score': 0.08774490654468536,
-  'token': 2535,
-  'token_str': 'role'},
- {'sequence': "[CLS] hello i'm a new model. [SEP]",
-  'score': 0.05338378623127937,
-  'token': 2047,
-  'token_str': 'new'},
- {'sequence': "[CLS] hello i'm a super model. [SEP]",
-  'score': 0.04667217284440994,
-  'token': 3565,
-  'token_str': 'super'},
- {'sequence': "[CLS] hello i'm a fine model. [SEP]",
-  'score': 0.027095865458250046,
-  'token': 2986,
-  'token_str': 'fine'}]
-```
-
-Here is how to use this model to get the features of a given text in PyTorch:
+# ONNX O4 Version of BGE-RERANKER-V2
 
 ```python
-from transformers import BertTokenizer, BertModel
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-model = BertModel.from_pretrained("bert-base-uncased")
-text = "Replace me by any text you'd like."
-encoded_input = tokenizer(text, return_tensors='pt')
-output = model(**encoded_input)
-```
-
-and in TensorFlow:
-
-```python
-from transformers import BertTokenizer, TFBertModel
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-model = TFBertModel.from_pretrained("bert-base-uncased")
-text = "Replace me by any text you'd like."
-encoded_input = tokenizer(text, return_tensors='tf')
-output = model(encoded_input)
-```
-
-### Limitations and bias
-
-Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
-predictions:
-
-```python
->>> from transformers import pipeline
->>> unmasker = pipeline('fill-mask', model='bert-base-uncased')
->>> unmasker("The man worked as a [MASK].")
-
-[{'sequence': '[CLS] the man worked as a carpenter. [SEP]',
-  'score': 0.09747550636529922,
-  'token': 10533,
-  'token_str': 'carpenter'},
- {'sequence': '[CLS] the man worked as a waiter. [SEP]',
-  'score': 0.0523831807076931,
-  'token': 15610,
-  'token_str': 'waiter'},
- {'sequence': '[CLS] the man worked as a barber. [SEP]',
-  'score': 0.04962705448269844,
-  'token': 13362,
-  'token_str': 'barber'},
- {'sequence': '[CLS] the man worked as a mechanic. [SEP]',
-  'score': 0.03788609802722931,
-  'token': 15893,
-  'token_str': 'mechanic'},
- {'sequence': '[CLS] the man worked as a salesman. [SEP]',
-  'score': 0.037680890411138535,
-  'token': 18968,
-  'token_str': 'salesman'}]
-
->>> unmasker("The woman worked as a [MASK].")
-
-[{'sequence': '[CLS] the woman worked as a nurse. [SEP]',
-  'score': 0.21981462836265564,
-  'token': 6821,
-  'token_str': 'nurse'},
- {'sequence': '[CLS] the woman worked as a waitress. [SEP]',
-  'score': 0.1597415804862976,
-  'token': 13877,
-  'token_str': 'waitress'},
- {'sequence': '[CLS] the woman worked as a maid. [SEP]',
-  'score': 0.1154729500412941,
-  'token': 10850,
-  'token_str': 'maid'},
- {'sequence': '[CLS] the woman worked as a prostitute. [SEP]',
-  'score': 0.037968918681144714,
-  'token': 19215,
-  'token_str': 'prostitute'},
- {'sequence': '[CLS] the woman worked as a cook. [SEP]',
-  'score': 0.03042375110089779,
-  'token': 5660,
-  'token_str': 'cook'}]
-```
-
-This bias will also affect all fine-tuned versions of this model.
-
-## Training data
-
-The BERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038
-unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and
-headers).
-
-## Training procedure
-
-### Preprocessing
-
-The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are
-then of the form:
-
-```
-[CLS] Sentence A [SEP] Sentence B [SEP]
-```
+pairs = [['Odio comer manzana.','I reallly like eating apple'],['I reallly like eating apple', 'Realmente me gusta comer manzana.'], ['I reallly like eating apple', 'I hate apples'],['Las manzanas son geniales.','Realmente me gusta comer manzana.']]
 
-With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in
-the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a
-consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two
-"sentences" has a combined length of less than 512 tokens.
+from optimum.onnxruntime import ORTModelForFeatureExtraction,ORTModelForSequenceClassification
+from transformers import AutoTokenizer
 
-The details of the masking procedure for each sentence are the following:
-- 15% of the tokens are masked.
-- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
-- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
-- In the 10% remaining cases, the masked tokens are left as is.
+model_checkpoint = "onnxO4_bge_reranker_v2_m3"
 
-### Pretraining
+ort_model = ORTModelForSequenceClassification.from_pretrained(model_checkpoint)
+tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
 
-The model was trained on 4 cloud TPUs in Pod configuration (16 TPU chips total) for one million steps with a batch size
-of 256. The sequence length was limited to 128 tokens for 90% of the steps and 512 for the remaining 10%. The optimizer
-used is Adam with a learning rate of 1e-4, \(eta_{1} = 0.9\) and \(eta_{2} = 0.999\), a weight decay of 0.01,
-learning rate warmup for 10,000 steps and linear decay of the learning rate after.
+# ONNX Results
+import torch
 
-## Evaluation results
 
-When fine-tuned on downstream tasks, this model achieves the following results:
+with torch.no_grad():
+    inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
+    scores = ort_model(**inputs, return_dict=True).logits.view(-1, ).float()
+    print(scores)
 
-Glue test results:
+## tensor([ -9.5081,  -3.9569, -10.8632,   0.3756])
 
-| Task | MNLI-(m/mm) | QQP  | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE  | Average |
-|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
-|      | 84.6/83.4   | 71.2 | 90.5 | 93.5  | 52.1 | 85.8  | 88.9 | 66.4 | 79.6    |
+# Original non quantized
 
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
-### BibTeX entry and citation info
+tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-v2-m3')
+model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-v2-m3')
+model.eval()
 
-```bibtex
-@article{DBLP:journals/corr/abs-1810-04805,
-  author    = {Jacob Devlin and
-               Ming{-}Wei Chang and
-               Kenton Lee and
-               Kristina Toutanova},
-  title     = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language
-               Understanding},
-  journal   = {CoRR},
-  volume    = {abs/1810.04805},
-  year      = {2018},
-  url       = {http://arxiv.org/abs/1810.04805},
-  archivePrefix = {arXiv},
-  eprint    = {1810.04805},
-  timestamp = {Tue, 30 Oct 2018 20:39:56 +0100},
-  biburl    = {https://dblp.org/rec/journals/corr/abs-1810-04805.bib},
-  bibsource = {dblp computer science bibliography, https://dblp.org}
-}
-```
+with torch.no_grad():
+    inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
+    scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
+    print(scores)
 
-<a href="https://huggingface.co/exbert/?model=bert-base-uncased">
-	<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
-</a>
-    
+## tensor([ -9.4973,  -3.9538, -10.8504,   0.3660])
+```