PeterV09 AndrewZeng commited on
Commit
7432de2
1 Parent(s): 6d3119d

Update README.md (#1)

Browse files

- Update README.md (f5900c7825a9574ec8439c51afbdb50ffcfe4bb6)


Co-authored-by: WeihaoZeng <AndrewZeng@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +30 -7
README.md CHANGED
@@ -25,23 +25,46 @@ Deita 7B V1.0 is a fine-tuned + DPO version of Mistral-7B-v0.1 that was trained
25
  - **Model Family:** Other models and the dataset are found in the [Deita collection](https://huggingface.co/collections/hkust-nlp/deita-6569c198c174808d94cf5bd4).
26
 
27
  ## Performance
28
- | Model | Align | Data Size | MT-Bench | AlpacaEval(%) | OpenLLM (Avg.) |
 
 
 
 
 
29
  |------------------------------------------------|-----------|------------|----------|---------------|----------------|
30
  | **Proprietary Models** | | | | | |
31
  | GPT-4-Turbo | ? | -- | 9.32 | 97.70 | -- |
32
  | GPT-4 | SFT + PPO | -- | 8.99 | 95.03 | -- |
33
  | Claude-2 | SFT + PPO | -- | 8.06 | 91.36 | -- |
34
  | GPT-3.5-turbo | SFT + PPO | -- | 7.94 | 89.37 | -- |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  | **Open-sourced Models based on Mistral-7B** | | | | | |
36
  | Mistral-7B-Instruct-v0.1 | -- | -- | 6.84 | 69.65 | 60.45 |
37
  | Zephyr-7B-sft | SFT | 200K SFT | 5.32 | 75.12 | 60.93 |
38
- | Zephyr-7B-beta | SFT + DPO | 200K SFT + 60K DPO | 7.34 | 90.60 | 66.36 |
39
- | OpenChat-3.5 | C-RLFT | >70K C-RLFT | 7.81 | 88.51 | -- |
40
- | Starling-7B | C-RLFT + APA | >70K C-RLFT + 183K APA | 8.09 | 91.99 | -- |
41
  | Random | SFT | 10K SFT | 5.89 | 56.90 | 61.72 |
42
- | DEITA-7B-v1.0-sft | SFT | 6K SFT | 7.22 | 80.78 | 64.94 |
43
- | DEITA-7B-v1.0-sft | SFT | 10K SFT | 7.32 | 81.67 | 64.00 |
44
- | DEITA-7B-v1.0 | SFT + DPO | 6K SFT + 10K DPO | 7.55 | 90.06 | 69.86 |
 
 
 
 
45
 
46
  ## Input Format
47
 
 
25
  - **Model Family:** Other models and the dataset are found in the [Deita collection](https://huggingface.co/collections/hkust-nlp/deita-6569c198c174808d94cf5bd4).
26
 
27
  ## Performance
28
+
29
+
30
+ <details>
31
+ <summary>See full evaluations</summary>
32
+
33
+ | Model | Align | Data Size | MT-Bench | AlpacaEval(%) | OpenLLM (Avg.) |
34
  |------------------------------------------------|-----------|------------|----------|---------------|----------------|
35
  | **Proprietary Models** | | | | | |
36
  | GPT-4-Turbo | ? | -- | 9.32 | 97.70 | -- |
37
  | GPT-4 | SFT + PPO | -- | 8.99 | 95.03 | -- |
38
  | Claude-2 | SFT + PPO | -- | 8.06 | 91.36 | -- |
39
  | GPT-3.5-turbo | SFT + PPO | -- | 7.94 | 89.37 | -- |
40
+ | **Open-sourced Models based on LLaMA-1-13B** | | | | | |
41
+ | LIMA | SFT | 1K SFT | 4.29 | 41.98 | 59.82 |
42
+ | WizardLM-13B | SFT | 70K SFT | 6.35 | 75.31 | 58.96 |
43
+ | Vicuna-13B-v1.3 | SFT | 125K SFT | 6.39 | 82.11 | 60.01 |
44
+ | Random | SFT | 10K SFT | 6.03 | 71.52 | 60.14 |
45
+ | DEITA-LLaMA1-13B-v1.0-sft | SFT | 10K SFT | 6.60 | 78.01 | 64.27 |
46
+ | **Open-sourced Models based on LLaMA-2-13B** | | | | | |
47
+ | Tulu-2-13B | SFT | 326K SFT | 6.70 | 78.90 | -- |
48
+ | Tulu-2-13B+DPO | SFT + DPO | 326K SFT + 60K DPO | 7.00 | 89.50 | -- |
49
+ | LLaMA2-13B-Chat | SFT + PPO | -- | 6.65 | 81.09 | -- |
50
+ | WizardLM-13B-v1.2 | SFT | >70K SFT | 7.09 | 89.17 | -- |
51
+ | Vicuna-13B-v1.5 | SFT | 125K SFT | 6.57 | 78.80 | 61.63 |
52
+ | Random | SFT | 10K SFT | 5.78 | 65.19 | 61.32 |
53
+ | DEITA-LLaMA2-13B-v1.0-sft | SFT | 10K SFT | 6.79 | 81.09 | 62.71 |
54
  | **Open-sourced Models based on Mistral-7B** | | | | | |
55
  | Mistral-7B-Instruct-v0.1 | -- | -- | 6.84 | 69.65 | 60.45 |
56
  | Zephyr-7B-sft | SFT | 200K SFT | 5.32 | 75.12 | 60.93 |
57
+ | $\text{Zephyr-7B-}\beta$ | SFT + DPO | 200K SFT + 60K DPO | 7.34 | 90.60 | 66.36 |
58
+ | OpenChat-3.5 | C-RLFT | >> 70K C-RLFT | 7.81 | 88.51 | -- |
59
+ | Starling-7B | C-RLFT + APA | >>70K C-RLFT + 183K APA | 8.09 | 91.99 | -- |
60
  | Random | SFT | 10K SFT | 5.89 | 56.90 | 61.72 |
61
+ | DEITA-7B-v1.0-sft (6K) | SFT | 6K SFT | 7.22 | 80.78 | 64.94 |
62
+ | DEITA-7B-v1.0-sft (10K) | SFT | 10K SFT | 7.32 | 81.67 | 64.00 |
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
70