Commit
•
915c599
1
Parent(s):
b30c8a2
Update README.md
Browse files
README.md
CHANGED
@@ -2819,7 +2819,7 @@ license: apache-2.0
|
|
2819 |
## News
|
2820 |
|
2821 |
|
2822 |
-
04/16/2024: Release the ** Arctic-
|
2823 |
|
2824 |
|
2825 |
## Models
|
@@ -2828,7 +2828,7 @@ license: apache-2.0
|
|
2828 |
Arctic-Embed is a suite of text embedding models that focuses on creating high-quality retrieval models optimized for performance.
|
2829 |
|
2830 |
|
2831 |
-
The `arctic-
|
2832 |
|
2833 |
|
2834 |
The models are trained by leveraging existing open-source text representation models, such as bert-base-uncased, and are trained in a multi-stage pipeline to optimize their retrieval performance. First, the models are trained with large batches of query-document pairs where negatives are derived in-batch—pretraining leverages about 400m samples of a mix of public datasets and proprietary web search data. Following pretraining models are further optimized with long training on a smaller dataset (about 1m samples) of triplets of query, positive document, and negative document derived from hard harmful mining. Mining of the negatives and data curation is crucial to retrieval accuracy. A detailed technical report will be available shortly.
|
@@ -2936,7 +2936,7 @@ Based on the [intfloat/e5-large-unsupervised](https://huggingface.co/intfloat/e5
|
|
2936 |
### Using Huggingface transformers
|
2937 |
|
2938 |
|
2939 |
-
|
2940 |
|
2941 |
|
2942 |
|
@@ -2977,7 +2977,7 @@ for query, query_scores in zip(queries, scores):
|
|
2977 |
```
|
2978 |
|
2979 |
|
2980 |
-
If you use the long context model
|
2981 |
|
2982 |
|
2983 |
``` py
|
@@ -2994,7 +2994,7 @@ TBD
|
|
2994 |
## Contact
|
2995 |
|
2996 |
|
2997 |
-
|
2998 |
You also can email Daniel Campos(daniel.campos@snowflake.com).
|
2999 |
|
3000 |
|
@@ -3007,7 +3007,11 @@ Arctic is licensed under the [Apache-2](https://www.apache.org/licenses/LICENSE-
|
|
3007 |
## Acknowledgement
|
3008 |
|
3009 |
|
3010 |
-
We
|
3011 |
-
|
|
|
|
|
|
|
|
|
3012 |
|
3013 |
|
|
|
2819 |
## News
|
2820 |
|
2821 |
|
2822 |
+
04/16/2024: Release the ** Arctic-embed ** family of text empedding models. The releases are state-of-the-art for Retrieval quality at each of their representative size profiles. [Technical Report]() is coming shortly. For more details, please refer to our Github: [Arctic-Text-Embed](https://github.com/Snowflake/Arctic-Text-Embed).
|
2823 |
|
2824 |
|
2825 |
## Models
|
|
|
2828 |
Arctic-Embed is a suite of text embedding models that focuses on creating high-quality retrieval models optimized for performance.
|
2829 |
|
2830 |
|
2831 |
+
The `arctic-embedding` models achieve **state-of-the-art performance on the MTEB/BEIR leaderboard** for each of their size variants. Evaluation is performed using these [scripts](https://github.com/Snowflake-Labs/arctic-embed/tree/main/src). As shown below, each class of model size achieves SOTA retrieval accuracy compared to other top models.
|
2832 |
|
2833 |
|
2834 |
The models are trained by leveraging existing open-source text representation models, such as bert-base-uncased, and are trained in a multi-stage pipeline to optimize their retrieval performance. First, the models are trained with large batches of query-document pairs where negatives are derived in-batch—pretraining leverages about 400m samples of a mix of public datasets and proprietary web search data. Following pretraining models are further optimized with long training on a smaller dataset (about 1m samples) of triplets of query, positive document, and negative document derived from hard harmful mining. Mining of the negatives and data curation is crucial to retrieval accuracy. A detailed technical report will be available shortly.
|
|
|
2936 |
### Using Huggingface transformers
|
2937 |
|
2938 |
|
2939 |
+
You can use the transformers package to use an arctic-embed model, as shown below. For optimal retrieval quality, use the CLS token to embed each text portion and use the query prefix below (just on the query).
|
2940 |
|
2941 |
|
2942 |
|
|
|
2977 |
```
|
2978 |
|
2979 |
|
2980 |
+
If you use the long context model with more than 2048 tokens, ensure that you initialize the model like below instead. This will use [RPE](https://arxiv.org/abs/2104.09864) to allow up to 8192 tokens.
|
2981 |
|
2982 |
|
2983 |
``` py
|
|
|
2994 |
## Contact
|
2995 |
|
2996 |
|
2997 |
+
Feel free to open an issue or pull request if you have any questions or suggestions about this project.
|
2998 |
You also can email Daniel Campos(daniel.campos@snowflake.com).
|
2999 |
|
3000 |
|
|
|
3007 |
## Acknowledgement
|
3008 |
|
3009 |
|
3010 |
+
We want to thank the open-source community, which has provided the great building blocks upon which we could make our models.
|
3011 |
+
We thank our modeling engineers, Danmei Xu, Luke Merrick, Gaurav Nuti, and Daniel Campos, for making these great models possible.
|
3012 |
+
We thank our leadership, Himabindu Pucha, Kelvin So, Vivek Raghunathan, and Sridhar Ramaswamy, for supporting this work.
|
3013 |
+
We also thank the open-source community for producing the great models we could build on top of and making these releases possible.
|
3014 |
+
Finally, we thank the researchers who created BEIR and MTEB benchmarks.
|
3015 |
+
It is largely thanks to their tireless work to define what better looks like that we could improve model performance.
|
3016 |
|
3017 |
|