spacemanidol commited on
Commit
b30c8a2
1 Parent(s): 19f9227

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -2801,7 +2801,7 @@ model-index:
2801
  value: 85.30624598674467
2802
  license: apache-2.0
2803
  ---
2804
- <h1 align="center">Snowflake's artic-embed-m</h1>
2805
  <h4 align="center">
2806
  <p>
2807
  <a href=#news>News</a> |
@@ -2825,7 +2825,7 @@ license: apache-2.0
2825
  ## Models
2826
 
2827
 
2828
- Arctic-Embed is a suite of text embedding models that focuses on creating high-quality embedding models for retrieval that are optimized for performance.
2829
 
2830
 
2831
  The `arctic-text-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 when compared to other top models.
@@ -2944,8 +2944,8 @@ To use an arctic-embed model, you can use the transformers package, as shown bel
2944
  import torch
2945
  from transformers import AutoModel, AutoTokenizer
2946
 
2947
- tokenizer = AutoTokenizer.from_pretrained('Snowflake/snow-text-embed-base')
2948
- model = AutoModel.from_pretrained('Snowflake/snow-text-embed-base', add_pooling_layer=False)
2949
  model.eval()
2950
 
2951
  query_prefix = 'Represent this sentence for searching relevant passages: '
@@ -2981,7 +2981,7 @@ If you use the long context model and have more than 2048 tokens, ensure that yo
2981
 
2982
 
2983
  ``` py
2984
- model = AutoModel.from_pretrained('Snowflake/[arctic-embed-s](https://huggingface.co/Snowflake/arctic-embed-m-long/)', trust_remote_code=True, rotary_scaling_factor=2)
2985
  ```
2986
 
2987
 
 
2801
  value: 85.30624598674467
2802
  license: apache-2.0
2803
  ---
2804
+ <h1 align="center">Snowflake's Artic-embed-m</h1>
2805
  <h4 align="center">
2806
  <p>
2807
  <a href=#news>News</a> |
 
2825
  ## Models
2826
 
2827
 
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-text-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 when compared to other top models.
 
2944
  import torch
2945
  from transformers import AutoModel, AutoTokenizer
2946
 
2947
+ tokenizer = AutoTokenizer.from_pretrained('Snowflake/arctic-embed-m')
2948
+ model = AutoModel.from_pretrained('Snowflake/arctic-embed-m', add_pooling_layer=False)
2949
  model.eval()
2950
 
2951
  query_prefix = 'Represent this sentence for searching relevant passages: '
 
2981
 
2982
 
2983
  ``` py
2984
+ model = AutoModel.from_pretrained('Snowflake/arctic-embed-m-long', trust_remote_code=True, rotary_scaling_factor=2)
2985
  ```
2986
 
2987