Update README.md

README.md

@@ -2602,10 +2602,51 @@ model-index:
       value: 78.02957839746892
 ---
 
-# nomic-embed-text-v1-unsupervised:  
+# nomic-embed-text-v1-unsupervised: A Reproducible Long Context (8192) Text Embedder 
 
 `nomic-embed-text-v1-unsupervised` is 8192 context length text encoder. This is a checkpoint after contrastive pretraining from multi-stage contrastive training of the
 [final model](https://huggingface.co/nomic-ai/nomic-embed-text-v1). If you want to extract embeddings, we suggest using [nomic-embed-text-v1](https://huggingface.co/nomic-ai/nomic-embed-text-v1)
 .
 
 If you would like to finetune a model on more data, you can use this model as an initialization
+
+
+## Training Details
+
+We train our embedder using a multi-stage training pipeline. Starting from a long-context [BERT model](https://huggingface.co/nomic-ai/nomic-bert-2048),
+the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles.
+
+In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage.
+
+For more details, see Nomic Embed [Technical Report](https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf).
+
+Training data to train the models is released in its entirety. For more details, see the `contrastors` [repository](https://github.com/nomic-ai/contrastors)
+
+## Usage
+
+
+```python
+import torch
+import torch.nn.functional as F
+from transformers import AutoTokenizer, AutoModel
+
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0]
+    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 = ['What is TSNE?', 'Who is Laurens van der Maaten?']
+
+tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
+model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1-unsupervised', trust_remote_code=True)
+
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+embeddings = F.normalize(embeddings, p=2, dim=1)
+print(embeddings)
+```
+