Update README.md
Browse files
README.md
CHANGED
|
@@ -6,15 +6,15 @@ tags:
|
|
| 6 |
# Diver-Retriever-4B
|
| 7 |
|
| 8 |
|
| 9 |
-
##
|
| 10 |
-
|
| 11 |
-
### HighLights
|
| 12 |
The Diver Retriever 4B model is a reasoning-intensive model designed to tackle the challenge of reasonIR and rader.
|
| 13 |
We combined data from the fields of mathematics, coding, and healthcare.
|
| 14 |
At the same time, we made precise matching in terms of the difficulty level of the samples, and uniquely
|
| 15 |
constructed negative samples corresponding to each field. Therefore, this model performs very well on the Bright LeaderBoard
|
| 16 |
as well as the Mteb-Medical Benchmark.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
### Model Description
|
| 19 |
|
| 20 |
<!-- Provide a longer summary of what this model is. -->
|
|
@@ -25,6 +25,7 @@ as well as the Mteb-Medical Benchmark.
|
|
| 25 |
- **Context Length:** 40k
|
| 26 |
- **Number of Paramaters:** 4B
|
| 27 |
|
|
|
|
| 28 |
|
| 29 |
## Evaluation
|
| 30 |
|
|
|
|
| 6 |
# Diver-Retriever-4B
|
| 7 |
|
| 8 |
|
| 9 |
+
## HighLights
|
|
|
|
|
|
|
| 10 |
The Diver Retriever 4B model is a reasoning-intensive model designed to tackle the challenge of reasonIR and rader.
|
| 11 |
We combined data from the fields of mathematics, coding, and healthcare.
|
| 12 |
At the same time, we made precise matching in terms of the difficulty level of the samples, and uniquely
|
| 13 |
constructed negative samples corresponding to each field. Therefore, this model performs very well on the Bright LeaderBoard
|
| 14 |
as well as the Mteb-Medical Benchmark.
|
| 15 |
|
| 16 |
+
|
| 17 |
+
|
| 18 |
### Model Description
|
| 19 |
|
| 20 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
|
| 25 |
- **Context Length:** 40k
|
| 26 |
- **Number of Paramaters:** 4B
|
| 27 |
|
| 28 |
+
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our GitHub (https://github.com/AQ-MedAI/Diver).
|
| 29 |
|
| 30 |
## Evaluation
|
| 31 |
|