Commit
•
de16c09
1
Parent(s):
dd4513e
Update README.md (#3)
Browse files- Update README.md (8ad4fa76c099397803667e7427ef9b0e0b4eba88)
Co-authored-by: WeihaoZeng <AndrewZeng@users.noreply.huggingface.co>
README.md
CHANGED
@@ -10,6 +10,8 @@ language:
|
|
10 |
|
11 |
# Model Card for Deita 7B V1.0
|
12 |
|
|
|
|
|
13 |
Deita is an open-sourced project designed to facilitate **Automatic Data Selection** for instruction tuning in Large Language Models (LLMs).
|
14 |
Deita 7B V1.0 is a fine-tuned + DPO version of Mistral-7B-v0.1 that was trained on **6K** automatically selected lightweight, high-quality alignment SFT data: [Deita 6K V0](https://huggingface.co/datasets/hkust-nlp/deita-6k-v0) and **10K** randomly sampled alignment preference data from Ultrafeedback.
|
15 |
|
@@ -27,8 +29,7 @@ Deita 7B V1.0 is a fine-tuned + DPO version of Mistral-7B-v0.1 that was trained
|
|
27 |
## Performance
|
28 |
|
29 |
|
30 |
-
|
31 |
-
<summary>See full evaluations</summary>
|
32 |
|
33 |
| Model | Align | Data Size | MT-Bench | AlpacaEval(%) | OpenLLM (Avg.) |
|
34 |
|------------------------------------------------|-----------|------------|----------|---------------|----------------|
|
@@ -63,7 +64,6 @@ Deita 7B V1.0 is a fine-tuned + DPO version of Mistral-7B-v0.1 that was trained
|
|
63 |
| DEITA-7B-v1.0 | SFT + DPO | 6K SFT + 10K DPO | 7.55 | 90.06 | 69.86 |
|
64 |
|
65 |
|
66 |
-
</details>
|
67 |
|
68 |
|
69 |
## Input Format
|
|
|
10 |
|
11 |
# Model Card for Deita 7B V1.0
|
12 |
|
13 |
+
[GitHub](https://github.com/hkust-nlp/deita) | [Paper](https://arxiv.org/abs/2312.15685)
|
14 |
+
|
15 |
Deita is an open-sourced project designed to facilitate **Automatic Data Selection** for instruction tuning in Large Language Models (LLMs).
|
16 |
Deita 7B V1.0 is a fine-tuned + DPO version of Mistral-7B-v0.1 that was trained on **6K** automatically selected lightweight, high-quality alignment SFT data: [Deita 6K V0](https://huggingface.co/datasets/hkust-nlp/deita-6k-v0) and **10K** randomly sampled alignment preference data from Ultrafeedback.
|
17 |
|
|
|
29 |
## Performance
|
30 |
|
31 |
|
32 |
+
|
|
|
33 |
|
34 |
| Model | Align | Data Size | MT-Bench | AlpacaEval(%) | OpenLLM (Avg.) |
|
35 |
|------------------------------------------------|-----------|------------|----------|---------------|----------------|
|
|
|
64 |
| DEITA-7B-v1.0 | SFT + DPO | 6K SFT + 10K DPO | 7.55 | 90.06 | 69.86 |
|
65 |
|
66 |
|
|
|
67 |
|
68 |
|
69 |
## Input Format
|