Files changed (1) hide show
  1. README.md +74 -2
README.md CHANGED
@@ -31,6 +31,78 @@ quantized_by: MaziyarPanahi
31
  <img src="https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1/resolve/main/logo.png" alt="Zephyr 141B Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
32
 
33
 
34
- # Model Card for zephyr-orpo-141b-A35b-v0.1-GGUF
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
 
36
- in progress ...
 
31
  <img src="https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1/resolve/main/logo.png" alt="Zephyr 141B Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
32
 
33
 
34
+ # zephyr-orpo-141b-A35b-v0.1-GGUF
35
+
36
+ On April 11th, [@HuggingFaceH4](https://huggingface.co/HuggingFaceH4) released a fine-tuned model called [HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1) based on `Mixtral-8x22B-v0.1` model.
37
+
38
+ - **Model type:** A Mixture of Experts (MoE) model with 141B total parameters and 35B active parameters. Fine-tuned on a mix of publicly available, synthetic datasets.
39
+ - **Language(s) (NLP):** Primarily English.
40
+ - **License:** Apache 2.0
41
+ - **Finetuned from model:** [mistral-community/Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1)
42
+
43
+
44
+ ## Load sharded model
45
+
46
+ `llama_load_model_from_file` will detect the number of files and will load additional tensors from the rest of files.
47
+
48
+ ```sh
49
+ llama.cpp/main -m zephyr-orpo-141b-A35b-v0.1.Q2_K-00001-of-00005.gguf --file prompt.txt -n 1024 -e
50
+ ```
51
+
52
+ The output from `Q2_K` quantized model:
53
+
54
+ ```
55
+ <|system|>
56
+ You are a helpful assistant.
57
+ <|user|>
58
+ Hello, how are you?
59
+ <|assistant|>
60
+ I'm doing great. How can I help you today?
61
+ <|user|>
62
+ Show me how to build a website in 10 simple steps
63
+ <|assistant|>
64
+ Of course, I'd be happy to guide you through the process of building a website in 10 simple steps.
65
+
66
+ 1. Determine the purpose of your website: Decide what your website will be used for, whether it's for business, personal use, or a blog.
67
+
68
+ 2. Choose a domain name: Your domain name is the address that people will use to find your website. It should be easy to remember and relevant to your website's purpose.
69
+
70
+ 3. Select a web hosting provider: A web hosting provider will store your website files and make them accessible to users around the world. Research different providers and choose one that fits your needs.
71
+
72
+ 4. Choose a platform: There are many platforms available for building a website, including WordPress, Wix, and Squarespace. Consider your technical skills and the features you need when choosing a platform.
73
+
74
+ 5. Plan your website structure: Decide on the pages you want to include on your website and how they will be organized. This will help guide the design process.
75
+
76
+ 6. Design your website: Use a template or create your own design for your website. Make sure it's visually appealing and easy to navigate.
77
+
78
+ 7. Add content to your website: Write the text and create images or videos for your website. Make sure the content is relevant to your website's purpose and engaging for users.
79
+
80
+ 8. Optimize your website for search engines: Make sure your website is easy to find by using keywords in your content and metadata. This will help your website rank higher in search engine results.
81
+
82
+ 9. Test your website: Test your website to make sure everything is working properly and that there are no broken links or errors.
83
+
84
+ 10. Launch your website: Once everything is working properly, it's time to launch your website. Share the link with your audience and start promoting your website.
85
+
86
+ I hope this guide helps you build a successful website. Let me know if you have any questions. [end of text]
87
+
88
+ llama_print_timings: load time = 11670.53 ms
89
+ llama_print_timings: sample time = 16.30 ms / 422 runs ( 0.04 ms per token, 25894.34 tokens per second)
90
+ llama_print_timings: prompt eval time = 5084.73 ms / 78 tokens ( 65.19 ms per token, 15.34 tokens per second)
91
+ llama_print_timings: eval time = 279055.53 ms / 421 runs ( 662.84 ms per token, 1.51 tokens per second)
92
+ llama_print_timings: total time = 284314.00 ms / 499 tokens
93
+ Log end
94
+ ```
95
+
96
+ What's inside the `prompt.txt`:
97
+ ```
98
+ <|system|>
99
+ You are a helpful assistant.</s>
100
+ <|user|>
101
+ Hello, how are you?</s>
102
+ <|assistant|>
103
+ I'm doing great. How can I help you today?</s>
104
+ <|user|>
105
+ Show me how to build a website in 10 simple steps</s>
106
+ <|assistant|>
107
+ ```
108