AndrewZeng commited on
Commit
f30fe3e
1 Parent(s): 2c2d434

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -6,6 +6,8 @@ license: apache-2.0
6
 
7
  # Model Card for Deita Quality Scorer
8
 
 
 
9
  Deita is an open-sourced project designed to facilitate Automatic Data Selection for instruction tuning in Large Language Models (LLMs).
10
 
11
  Deita Quality Scorer is a tool for automatically annotating the Instruction Quality of SFT data.
@@ -25,8 +27,6 @@ Deita Quality Scorer is a tool for automatically annotating the Instruction Qual
25
  ## Performance
26
 
27
 
28
- <details>
29
- <summary>See full evaluations</summary>
30
 
31
  | Model | Align | Data Size | MT-Bench | AlpacaEval(%) | OpenLLM (Avg.) |
32
  |------------------------------------------------|-----------|------------|----------|---------------|----------------|
@@ -61,7 +61,7 @@ Deita Quality Scorer is a tool for automatically annotating the Instruction Qual
61
  | DEITA-7B-v1.0 | SFT + DPO | 6K SFT + 10K DPO | 7.55 | 90.06 | 69.86 |
62
 
63
 
64
- </details>
65
 
66
 
67
  ## Usage
 
6
 
7
  # Model Card for Deita Quality Scorer
8
 
9
+ [GitHub](https://github.com/hkust-nlp/deita) | [Paper](https://arxiv.org/abs/2312.15685)
10
+
11
  Deita is an open-sourced project designed to facilitate Automatic Data Selection for instruction tuning in Large Language Models (LLMs).
12
 
13
  Deita Quality Scorer is a tool for automatically annotating the Instruction Quality of SFT data.
 
27
  ## Performance
28
 
29
 
 
 
30
 
31
  | Model | Align | Data Size | MT-Bench | AlpacaEval(%) | OpenLLM (Avg.) |
32
  |------------------------------------------------|-----------|------------|----------|---------------|----------------|
 
61
  | DEITA-7B-v1.0 | SFT + DPO | 6K SFT + 10K DPO | 7.55 | 90.06 | 69.86 |
62
 
63
 
64
+
65
 
66
 
67
  ## Usage