GGUF
GGUF
Imatrix
Quantized
Inference Endpoints
ABX-AI commited on
Commit
d8b108b
β€’
1 Parent(s): 240f2ee

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +107 -0
README.md CHANGED
@@ -1,3 +1,110 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - GGUF
5
+ - Imatrix
6
+ - Quantized
7
  ---
8
+ ================================================================================================================================================================================
9
+
10
+ <p style="font-size:20px;" align="center">
11
+ GGUF / IQ / Imatrix for microsoft/WizardLM-2-7B
12
+ </p>
13
+ ================================================================================================================================================================================
14
+ <p style="font-size:20px;" align="center">
15
+ 🏠 <a href="https://wizardlm.github.io/WizardLM2" target="_blank">WizardLM-2 Release Blog</a> </p>
16
+ <p align="center">
17
+ πŸ€— <a href="https://huggingface.co/collections/microsoft/wizardlm-2-661d403f71e6c8257dbd598a" target="_blank">HF Repo</a> β€’πŸ± <a href="https://github.com/victorsungo/WizardLM/tree/main/WizardLM-2" target="_blank">Github Repo</a> β€’ 🐦 <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> β€’ πŸ“ƒ <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> β€’ πŸ“ƒ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> β€’ πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br>
18
+ </p>
19
+ <p align="center">
20
+ πŸ‘‹ Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>
21
+ </p>
22
+
23
+
24
+
25
+ ## News πŸ”₯πŸ”₯πŸ”₯ [2024/04/15]
26
+
27
+ We introduce and opensource WizardLM-2, our next generation state-of-the-art large language models,
28
+ which have improved performance on complex chat, multilingual, reasoning and agent.
29
+ New family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B.
30
+
31
+ - WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works
32
+ and consistently outperforms all the existing state-of-the-art opensource models.
33
+ - WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size.
34
+ - WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.
35
+
36
+ For more details of WizardLM-2 please read our [release blog post](https://wizardlm.github.io/WizardLM2) and upcoming paper.
37
+
38
+
39
+ ## Model Details
40
+
41
+ * **Model name**: WizardLM-2 7B
42
+ * **Developed by**: WizardLM@Microsoft AI
43
+ * **Base model**: [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
44
+ * **Parameters**: 7B
45
+ * **Language(s)**: Multilingual
46
+ * **Blog**: [Introducing WizardLM-2](https://wizardlm.github.io/WizardLM2)
47
+ * **Repository**: [https://github.com/nlpxucan/WizardLM](https://github.com/nlpxucan/WizardLM)
48
+ * **Paper**: WizardLM-2 (Upcoming)
49
+ * **License**: Apache2.0
50
+
51
+
52
+
53
+ ## Model Capacities
54
+
55
+
56
+ **MT-Bench**
57
+
58
+ We also adopt the automatic MT-Bench evaluation framework based on GPT-4 proposed by lmsys to assess the performance of models.
59
+ The WizardLM-2 8x22B even demonstrates highly competitive performance compared to the most advanced proprietary models.
60
+ 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.
61
+
62
+ <p align="center" width="100%">
63
+ <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>
64
+ </p>
65
+
66
+
67
+ **Human Preferences Evaluation**
68
+
69
+ 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.
70
+ We report the win:loss rate without tie:
71
+
72
+ - WizardLM-2 8x22B is just slightly falling behind GPT-4-1106-preview, and significantly stronger than Command R Plus and GPT4-0314.
73
+ - WizardLM-2 70B is better than GPT4-0613, Mistral-Large, and Qwen1.5-72B-Chat.
74
+ - WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta.
75
+
76
+ <p align="center" width="100%">
77
+ <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>
78
+ </p>
79
+
80
+
81
+
82
+
83
+
84
+ ## Method Overview
85
+ 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.
86
+
87
+ <p align="center" width="100%">
88
+ <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>
89
+ </p>
90
+
91
+
92
+
93
+
94
+
95
+ ## Usage
96
+
97
+ ❗<b>Note for model system prompts usage:</b>
98
+
99
+
100
+ <b>WizardLM-2</b> adopts the prompt format from <b>Vicuna</b> and supports **multi-turn** conversation. The prompt should be as following:
101
+
102
+ ```
103
+ A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful,
104
+ detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
105
+ USER: Who are you? ASSISTANT: I am WizardLM.</s>......
106
+ ```
107
+
108
+ <b> Inference WizardLM-2 Demo Script</b>
109
+
110
+ We provide a WizardLM-2 inference demo [code](https://github.com/nlpxucan/WizardLM/tree/main/demo) on our github.