Total runs:
3.1K
Run Growth:
597
Growth Rate:
19.06%
Sponsored by
Vmake Labs Video Enhancer
KnutJaegersberg / WizardLM-2-8x22B
Model's Last Updated: April 16 2024
text-generation
Introduction of WizardLM-2-8x22B
Model Details of WizardLM-2-8x22B
🤗
HF Repo
•🐱
Github Repo
• 🐦
Twitter
• 📃
[WizardLM]
• 📃
[WizardCoder]
• 📃
[WizardMath]
👋 Join our Discord
News 🔥🔥🔥 [2024/04/15]
We introduce and opensource WizardLM-2, our next generation state-of-the-art large language models, which have improved performance on complex chat, multilingual, reasoning and agent. New family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B.
- WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works and consistently outperforms all the existing state-of-the-art opensource models.
- WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size.
- WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.
For more details of WizardLM-2 please read our release blog post and upcoming paper.
Model Details
- Model name : WizardLM-2 8x22B
- Developed by : WizardLM@Microsoft AI
- Model type : Mixture of Experts (MoE)
- Base model : mistral-community/Mixtral-8x22B-v0.1
- Parameters : 141B
- Language(s) : Multilingual
- Blog : Introducing WizardLM-2
- Repository : https://github.com/nlpxucan/WizardLM
- Paper : WizardLM-2 (Upcoming)
- License : Apache2.0
Model Capacities
MT-Bench
We also adopt the automatic MT-Bench evaluation framework based on GPT-4 proposed by lmsys to assess the performance of models. The WizardLM-2 8x22B even demonstrates highly competitive performance compared to the most advanced proprietary models. 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.
Human Preferences Evaluation
We carefully collected a complex and challenging set consisting of real-world instructions, which includes main requirements of humanity, such as writing, coding, math, reasoning, agent, and multilingual. We report the win:loss rate without tie:
- WizardLM-2 8x22B is just slightly falling behind GPT-4-1106-preview, and significantly stronger than Command R Plus and GPT4-0314.
- WizardLM-2 70B is better than GPT4-0613, Mistral-Large, and Qwen1.5-72B-Chat.
- WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta.
Method Overview
We built a fully AI powered synthetic training system to train WizardLM-2 models, please refer to our blog for more details of this system.
Usage
❗ Note for model system prompts usage:
WizardLM-2 adopts the prompt format from Vicuna and supports multi-turn conversation. The prompt should be as following:
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful,
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
USER: Who are you? ASSISTANT: I am WizardLM.</s>......
Inference WizardLM-2 Demo Script
We provide a WizardLM-2 inference demo code on our github.
Runs of KnutJaegersberg WizardLM-2-8x22B on huggingface.co
20
Total runs
0
24-hour runs
0
3-day runs
-20
7-day runs
-16
30-day runs
More Information About WizardLM-2-8x22B huggingface.co Model
Url of WizardLM-2-8x22B
WizardLM-2-8x22B huggingface.co Url
Provider of WizardLM-2-8x22B huggingface.co
Other API from KnutJaegersberg
Updated:March 08 2024
Total runs:
1.4K
Run Growth:
-291
Growth Rate:
-20.61%
Total runs:
1.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.2K
Run Growth:
-157
Growth Rate:
-13.06%
Total runs:
1.1K
Run Growth:
-242
Growth Rate:
-19.21%
Total runs:
1.0K
Run Growth:
97
Growth Rate:
9.32%
Total runs:
991
Run Growth:
983
Growth Rate:
99.19%
Total runs:
850
Run Growth:
0
Growth Rate:
0.00%
Total runs:
825
Run Growth:
235
Growth Rate:
28.48%
Total runs:
399
Run Growth:
-428
Growth Rate:
-107.27%
Total runs:
392
Run Growth:
-423
Growth Rate:
-107.91%
Total runs:
348
Run Growth:
0
Growth Rate:
0.00%
Total runs:
266
Run Growth:
232
Growth Rate:
87.22%
Total runs:
253
Run Growth:
147
Growth Rate:
58.10%
Total runs:
246
Run Growth:
49
Growth Rate:
19.92%
Total runs:
236
Run Growth:
-235
Growth Rate:
-99.58%
Total runs:
233
Run Growth:
32
Growth Rate:
13.68%
Total runs:
232
Run Growth:
25
Growth Rate:
10.78%
Total runs:
231
Run Growth:
23
Growth Rate:
9.87%
Total runs:
229
Run Growth:
-248
Growth Rate:
-108.30%
Total runs:
227
Run Growth:
-245
Growth Rate:
-107.93%
Total runs:
225
Run Growth:
39
Growth Rate:
17.18%
Total runs:
221
Run Growth:
-252
Growth Rate:
-114.03%
Total runs:
220
Run Growth:
-254
Growth Rate:
-115.45%
Total runs:
219
Run Growth:
56
Growth Rate:
25.57%
Total runs:
213
Run Growth:
59
Growth Rate:
27.83%
Total runs:
213
Run Growth:
-206
Growth Rate:
-96.71%
Total runs:
205
Run Growth:
21
Growth Rate:
10.34%
Total runs:
190
Run Growth:
0
Growth Rate:
0.00%
Total runs:
189
Run Growth:
4
Growth Rate:
2.13%
Total runs:
183
Run Growth:
124
Growth Rate:
67.76%
Total runs:
169
Run Growth:
0
Growth Rate:
0.00%
Total runs:
143
Run Growth:
-9
Growth Rate:
-6.29%
Total runs:
133
Run Growth:
67
Growth Rate:
50.38%
Total runs:
124
Run Growth:
-54
Growth Rate:
-43.55%
Total runs:
117
Run Growth:
53
Growth Rate:
45.30%
Total runs:
113
Run Growth:
27
Growth Rate:
21.95%
Total runs:
106
Run Growth:
-47
Growth Rate:
-45.19%
Total runs:
96
Run Growth:
-26
Growth Rate:
-27.08%
Total runs:
93
Run Growth:
-39
Growth Rate:
-41.94%
Total runs:
92
Run Growth:
92
Growth Rate:
100.00%
Total runs:
90
Run Growth:
-24
Growth Rate:
-26.67%
Total runs:
88
Run Growth:
6
Growth Rate:
6.98%
Total runs:
77
Run Growth:
-30
Growth Rate:
-38.96%
Total runs:
77
Run Growth:
29
Growth Rate:
37.66%
Total runs:
75
Run Growth:
-7
Growth Rate:
-9.33%
Total runs:
74
Run Growth:
-2
Growth Rate:
-2.67%
Total runs:
73
Run Growth:
8
Growth Rate:
11.27%
Total runs:
68
Run Growth:
0
Growth Rate:
0.00%
Total runs:
67
Run Growth:
-10
Growth Rate:
-14.93%
Total runs:
67
Run Growth:
-41
Growth Rate:
-61.19%
Total runs:
66
Run Growth:
-10
Growth Rate:
-15.15%
Total runs:
61
Run Growth:
15
Growth Rate:
24.59%
Total runs:
61
Run Growth:
-50
Growth Rate:
-81.97%
Total runs:
59
Run Growth:
-54
Growth Rate:
-91.53%
Total runs:
58
Run Growth:
-60
Growth Rate:
-103.45%
Total runs:
57
Run Growth:
-21
Growth Rate:
-36.84%
Total runs:
52
Run Growth:
-54
Growth Rate:
-103.85%
Total runs:
47
Run Growth:
0
Growth Rate:
0.00%
Total runs:
47
Run Growth:
35
Growth Rate:
74.47%
Total runs:
44
Run Growth:
22
Growth Rate:
50.00%
Total runs:
42
Run Growth:
-9
Growth Rate:
-21.43%
Total runs:
41
Run Growth:
23
Growth Rate:
56.10%
Total runs:
33
Run Growth:
18
Growth Rate:
54.55%
Total runs:
31
Run Growth:
13
Growth Rate:
41.94%
Total runs:
29
Run Growth:
-2
Growth Rate:
-6.90%
Total runs:
24
Run Growth:
4
Growth Rate:
16.67%
Total runs:
24
Run Growth:
13
Growth Rate:
54.17%
Total runs:
24
Run Growth:
4
Growth Rate:
16.67%
Total runs:
22
Run Growth:
7
Growth Rate:
35.00%
Total runs:
22
Run Growth:
-7
Growth Rate:
-31.82%
Total runs:
22
Run Growth:
4
Growth Rate:
18.18%
Total runs:
21
Run Growth:
13
Growth Rate:
61.90%
Total runs:
20
Run Growth:
6
Growth Rate:
31.58%
Total runs:
20
Run Growth:
-1
Growth Rate:
-5.00%
Total runs:
19
Run Growth:
3
Growth Rate:
17.65%
Total runs:
19
Run Growth:
3
Growth Rate:
15.79%
Total runs:
19
Run Growth:
2
Growth Rate:
10.53%
Total runs:
19
Run Growth:
-2
Growth Rate:
-10.00%
Total runs:
18
Run Growth:
13
Growth Rate:
72.22%
Total runs:
18
Run Growth:
-2
Growth Rate:
-10.53%
Total runs:
17
Run Growth:
-1
Growth Rate:
-5.88%
Total runs:
16
Run Growth:
-2
Growth Rate:
-12.50%
Total runs:
16
Run Growth:
5
Growth Rate:
31.25%
Total runs:
16
Run Growth:
6
Growth Rate:
37.50%
Total runs:
16
Run Growth:
-5
Growth Rate:
-31.25%
Total runs:
15
Run Growth:
1
Growth Rate:
6.67%
Total runs:
15
Run Growth:
11
Growth Rate:
73.33%
Total runs:
15
Run Growth:
6
Growth Rate:
46.15%
Total runs:
14
Run Growth:
7
Growth Rate:
50.00%