lamhieu commited on
Commit
76bcc54
•
1 Parent(s): f33f60b

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - vi
5
+ license: other
6
+ license_name: ghost-7b
7
+ license_link: https://ghost-x.vercel.app/ghost-7b-license
8
+ library_name: transformers
9
+ tags:
10
+ - ghost
11
+ - tools
12
+ - chat
13
+ pipeline_tag: text-generation
14
+ widget:
15
+ - text: Why is the sky blue ?
16
+ output:
17
+ text: >-
18
+ The sky appears blue because of a phenomenon called Rayleigh scattering.
19
+ Sunlight is composed of all colors of the visible spectrum, but blue light
20
+ has a shorter wavelength than other colors. When sunlight enters the
21
+ Earth's atmosphere, it interacts with molecules of nitrogen and oxygen,
22
+ which are the main components of our atmosphere. These molecules scatter
23
+ the shorter wavelengths of light, such as blue and violet, more than the
24
+ longer wavelengths, such as red and orange. As a result, when we look up
25
+ at the sky, we see more blue light than other colors because the blue
26
+ light has been scattered more by the molecules in the atmosphere.
27
+ ---
28
+
29
+ # Ghost 7B Alpha
30
+
31
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/600ae38cc92b79f54efd4556/QPrQZMQX_jzyYngmreP0_.jpeg" alt="Ghost 7B Alpha Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
32
+
33
+ The large generation of language models focuses on optimizing excellent reasoning, multi-task knowledge, and tools support.
34
+
35
+ # Introduction
36
+
37
+ **Ghost 7B Alpha** is a large language model fine-tuned from Mistral 7B, with a size of 7 billion parameters. The model was developed with the goal of optimizing reasoning ability, multi-task knowledge and supporting tool usage. The model works well with the main trained and optimized languages being English and Vietnamese.
38
+
39
+ Overall, the model is suitable when making a pretrained version so you can continue to develop the desired tasks, develop virtual assistants, perform features on tasks such as coding, translation, answering questions, creating documents, etc. It is truly an efficient, fast and extremely cheap open model.
40
+
41
+ ## Specifications
42
+
43
+ - Name: **Ghost 7B Alpha**.
44
+ - Model size: 7 billion parameters.
45
+ - Context length: 8K, 8192.
46
+ - Languages: English and Vietnamese.
47
+ - Main tasks: reasoning, multi-tasking knowledge and function tools.
48
+ - License: [Ghost 7B LICENSE AGREEMENT](https://ghost-x.vercel.app/ghost-7b-license).
49
+ - Based on: Mistral 7B.
50
+ - Distributions: Standard (BF16), GGUF, AWQ.
51
+ - Developed by: **Ghost X**, [Hieu Lam](https://huggingface.co/lamhieu).
52
+
53
+ ### Links
54
+
55
+ - Card model: [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha).
56
+ - Official website: [Ghost 7B Alpha](https://ghost-x.vercel.app/docs/models/ghost-7b-alpha/).
57
+ - Demo: [Playground with Ghost 7B Alpha](https://ghost-x.vercel.app/docs/notebooks/playground-with-ghost-7b-alpha/).
58
+
59
+ ## Distributions
60
+
61
+ We create many distributions to give you the best access options that best suit your needs. Always make sure you know which version you need and what will help you operate better.
62
+
63
+ | Version | Model card |
64
+ | ------- | -------------------------------------------------------------------- |
65
+ | BF16 | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha) |
66
+ | GGUF | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha-gguf) |
67
+ | AWQ | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha-awq) |
68
+
69
+ ## Note
70
+
71
+ For all official information and updates about the model, see here:
72
+ - Card model: [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha).
73
+ - Official website: [Ghost 7B Alpha](https://ghost-x.vercel.app/docs/models/ghost-7b-alpha/).
74
+ - Demo: [Playground with Ghost 7B Alpha](https://ghost-x.vercel.app/docs/notebooks/playground-with-ghost-7b-alpha/).