Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,10 @@ For the Qwen base model, we implemented the following modifications:
|
|
| 29 |
1. Replaced causal attention with bidirectional attention and constructed a new QZhouModel module based on Qwen2Model;
|
| 30 |
2. Modified the tokenizer's padding_side to "left".
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
## Usage
|
| 33 |
### Completely reproduce the benchmark results
|
| 34 |
We provide detailed parameters and environment configurations so that you can run results that are completely consistent with the mteb leaderboard on your own machine, including configurations such as environment dependencies and model arguments.
|
|
@@ -166,8 +170,8 @@ Our initial research experiments commenced prior to the release of Qwen3. To mai
|
|
| 166 |
|
| 167 |
### Citation
|
| 168 |
If you find our work worth citing, please use the following citation:
|
| 169 |
-
|
| 170 |
-
|
| 171 |
**Qwen2.5-7B-Instruct:**
|
| 172 |
```
|
| 173 |
@misc{qwen2.5,
|
|
|
|
| 29 |
1. Replaced causal attention with bidirectional attention and constructed a new QZhouModel module based on Qwen2Model;
|
| 30 |
2. Modified the tokenizer's padding_side to "left".
|
| 31 |
|
| 32 |
+
## MTEB/CMTEB Results
|
| 33 |
+
<img src="assets/image-2.png" width="800" height="300"></img>
|
| 34 |
+
|
| 35 |
+
|
| 36 |
## Usage
|
| 37 |
### Completely reproduce the benchmark results
|
| 38 |
We provide detailed parameters and environment configurations so that you can run results that are completely consistent with the mteb leaderboard on your own machine, including configurations such as environment dependencies and model arguments.
|
|
|
|
| 170 |
|
| 171 |
### Citation
|
| 172 |
If you find our work worth citing, please use the following citation:
|
| 173 |
+
**Technical Report:**
|
| 174 |
+
Coming soon...<br>
|
| 175 |
**Qwen2.5-7B-Instruct:**
|
| 176 |
```
|
| 177 |
@misc{qwen2.5,
|