xzuyn commited on
Commit
33e01d6
1 Parent(s): c209267

Replace links with ones from Wayback Machine

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -25,7 +25,7 @@ and consistently outperforms all the existing state-of-the-art opensource models
25
  - WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size.
26
  - WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.
27
 
28
- For more details of WizardLM-2 please read our [release blog post](https://wizardlm.github.io/WizardLM2) and upcoming paper.
29
 
30
 
31
  ## Model Details
@@ -36,7 +36,7 @@ For more details of WizardLM-2 please read our [release blog post](https://wiza
36
  * **Base model**: [mistral-community/Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1)
37
  * **Parameters**: 141B
38
  * **Language(s)**: Multilingual
39
- * **Blog**: [Introducing WizardLM-2](https://wizardlm.github.io/WizardLM2)
40
  * **Repository**: [https://github.com/nlpxucan/WizardLM](https://github.com/nlpxucan/WizardLM)
41
  * **Paper**: WizardLM-2 (Upcoming)
42
  * **License**: Apache2.0
@@ -52,7 +52,7 @@ The WizardLM-2 8x22B even demonstrates highly competitive performance compared t
52
  Meanwhile, WizardLM-2 7B and WizardLM-2 70B are all the top-performing models among the other leading baselines at 7B to 70B model scales.
53
 
54
  <p align="center" width="100%">
55
- <a ><img src="https://raw.githubusercontent.com/WizardLM/WizardLM2/main/static/images/mtbench.png" alt="MTBench" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>
56
  </p>
57
 
58
 
@@ -66,7 +66,7 @@ We report the win:loss rate without tie:
66
  - WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta.
67
 
68
  <p align="center" width="100%">
69
- <a ><img src="https://raw.githubusercontent.com/WizardLM/WizardLM2/main/static/images/winall.png" alt="Win" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>
70
  </p>
71
 
72
 
@@ -74,10 +74,10 @@ We report the win:loss rate without tie:
74
 
75
 
76
  ## Method Overview
77
- We built a **fully AI powered synthetic training system** to train WizardLM-2 models, please refer to our [blog](https://wizardlm.github.io/WizardLM2) for more details of this system.
78
 
79
  <p align="center" width="100%">
80
- <a ><img src="https://raw.githubusercontent.com/WizardLM/WizardLM2/main/static/images/exp_1.png" alt="Method" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>
81
  </p>
82
 
83
 
 
25
  - WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size.
26
  - WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.
27
 
28
+ For more details of WizardLM-2 please read our [release blog post](https://web.archive.org/web/20240415221214/https://wizardlm.github.io/WizardLM2/) and upcoming paper.
29
 
30
 
31
  ## Model Details
 
36
  * **Base model**: [mistral-community/Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1)
37
  * **Parameters**: 141B
38
  * **Language(s)**: Multilingual
39
+ * **Blog**: [Introducing WizardLM-2](https://web.archive.org/web/20240415221214/https://wizardlm.github.io/WizardLM2/)
40
  * **Repository**: [https://github.com/nlpxucan/WizardLM](https://github.com/nlpxucan/WizardLM)
41
  * **Paper**: WizardLM-2 (Upcoming)
42
  * **License**: Apache2.0
 
52
  Meanwhile, WizardLM-2 7B and WizardLM-2 70B are all the top-performing models among the other leading baselines at 7B to 70B model scales.
53
 
54
  <p align="center" width="100%">
55
+ <a ><img src="https://web.archive.org/web/20240415175608im_/https://wizardlm.github.io/WizardLM2/static/images/mtbench.png" alt="MTBench" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>
56
  </p>
57
 
58
 
 
66
  - WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta.
67
 
68
  <p align="center" width="100%">
69
+ <a ><img src="https://web.archive.org/web/20240415163303im_/https://wizardlm.github.io/WizardLM2/static/images/winall.png" alt="Win" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>
70
  </p>
71
 
72
 
 
74
 
75
 
76
  ## Method Overview
77
+ We built a **fully AI powered synthetic training system** to train WizardLM-2 models, please refer to our [blog](https://web.archive.org/web/20240415221214/https://wizardlm.github.io/WizardLM2/) for more details of this system.
78
 
79
  <p align="center" width="100%">
80
+ <a ><img src="https://web.archive.org/web/20240415163303im_/https://wizardlm.github.io/WizardLM2/static/images/exp_1.png" alt="Method" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>
81
  </p>
82
 
83