Upload folder using huggingface_hub
Browse files- README.md +0 -4
- config_sentence_transformers.json +1 -1
README.md
CHANGED
@@ -5516,10 +5516,6 @@ model-index:
|
|
5516 |
type: Retrieval
|
5517 |
---
|
5518 |
|
5519 |
-
# Introduction
|
5520 |
-
**This model is built upon [Alibaba-NLP/gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct). The key difference from the original model is the inclusion of a default prompt name in the model configuration file. This adjustment is particularly useful when serving the model, as the default prompt will automatically be prepended to each incoming document.**
|
5521 |
-
|
5522 |
-
|
5523 |
## gte-Qwen2-7B-instruct
|
5524 |
|
5525 |
**gte-Qwen2-7B-instruct** is the latest model in the gte (General Text Embedding) model family that ranks **No.1** in both English and Chinese evaluations on the Massive Text Embedding Benchmark [MTEB benchmark](https://huggingface.co/spaces/mteb/leaderboard) (as of June 16, 2024).
|
|
|
5516 |
type: Retrieval
|
5517 |
---
|
5518 |
|
|
|
|
|
|
|
|
|
5519 |
## gte-Qwen2-7B-instruct
|
5520 |
|
5521 |
**gte-Qwen2-7B-instruct** is the latest model in the gte (General Text Embedding) model family that ranks **No.1** in both English and Chinese evaluations on the Massive Text Embedding Benchmark [MTEB benchmark](https://huggingface.co/spaces/mteb/leaderboard) (as of June 16, 2024).
|
config_sentence_transformers.json
CHANGED
@@ -7,5 +7,5 @@
|
|
7 |
"prompts": {
|
8 |
"query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: "
|
9 |
},
|
10 |
-
"default_prompt_name":
|
11 |
}
|
|
|
7 |
"prompts": {
|
8 |
"query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: "
|
9 |
},
|
10 |
+
"default_prompt_name": null
|
11 |
}
|