Upload README.md

README.md

@@ -9076,7 +9076,9 @@ Key Features:
 
 3. Compression-friendly: Achieves high-quality retrieval with embeddings as small as 128 bytes/vector using Matryoshka Representation Learning (MRL) and quantization-aware embedding training.
 
-4. Drop-In Replacement: arctic-embed-l-v2.0 builds on [XMLR-Large](https://huggingface.co/FacebookAI/xlm-roberta-large) which allows direct drop-in inference replacement with any form of new libraries, kernels, inference engines etc. 
+4. Drop-In Replacement: arctic-embed-l-v2.0 builds on BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) which allows direct drop-in inference replacement with any form of new libraries, kernels, inference engines etc. 
+
+5. Long Context Support: arctic-embed-l-v2.0 builds on [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) which can support a context window of up to 8192 via the use of RoPE. 
 
 
 ### Quality Benchmarks
@@ -9151,10 +9153,10 @@ model.eval()
 query_prefix = 'query: '
 queries  = ['what is snowflake?', 'Where can I get the best tacos?']
 queries_with_prefix = ["{}{}".format(query_prefix, i) for i in queries]
-query_tokens = tokenizer(queries_with_prefix, padding=True, truncation=True, return_tensors='pt', max_length=512)
+query_tokens = tokenizer(queries_with_prefix, padding=True, truncation=True, return_tensors='pt', max_length=8192)
 
 documents = ['The Data Cloud!', 'Mexico City of Course!']
-document_tokens =  tokenizer(documents, padding=True, truncation=True, return_tensors='pt', max_length=512)
+document_tokens =  tokenizer(documents, padding=True, truncation=True, return_tensors='pt', max_length=8192)
 
 # Compute token embeddings
 with torch.no_grad():