Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,97 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- zh
|
6 |
+
tags:
|
7 |
+
- text-generation-inference
|
8 |
---
|
9 |
+
### LucasInsight/Meta-Llama-3.1-8B-Instruct Model Card
|
10 |
+
|
11 |
+
**Model Overview**
|
12 |
+
|
13 |
+
The LucasInsight/Meta-Llama-3.1-8B-Instruct model is an enhanced version of the Meta-Llama3 project, incorporating the alpaca-gpt4-data-zh Chinese dataset. The model has been fine-tuned using Unsloth with 4-bit QLoRA and generates GGUF model files compatible with the Ollama inference engine.
|
14 |
+
|
15 |
+
**模型概述**
|
16 |
+
|
17 |
+
LucasInsight/Meta-Llama-3.1-8B-Instruct 模型是在 Meta-Llama3 工程的基础上,增加了 alpaca-gpt4-data-zh 中文数据集。该模型通过使用 Unsloth 的 4-bit QLoRA 进行微调,生成的 GGUF 模型文件支持 Ollama 推理引擎。
|
18 |
+
|
19 |
+
**License Information**
|
20 |
+
|
21 |
+
This project is governed by the licenses of the integrated components:
|
22 |
+
|
23 |
+
1. **Meta-Llama3 Project**
|
24 |
+
- Project URL: [https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
|
25 |
+
- License: Llama 3 Community License Agreement
|
26 |
+
|
27 |
+
**Citation:**
|
28 |
+
```
|
29 |
+
@article{llama3modelcard,
|
30 |
+
title={Llama 3 Model Card},
|
31 |
+
author={AI@Meta},
|
32 |
+
year={2024},
|
33 |
+
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
|
34 |
+
}
|
35 |
+
```
|
36 |
+
|
37 |
+
2. **Unsloth Project**
|
38 |
+
- License: Apache-2.0 License
|
39 |
+
- Project URL: [https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit)
|
40 |
+
|
41 |
+
3. **Chinese Dataset Integration**
|
42 |
+
- Dataset: alpaca-gpt4-data-zh
|
43 |
+
- License: CC BY NC 4.0 (for non-commercial research use only)
|
44 |
+
- Dataset URL: [https://huggingface.co/datasets/llm-wizard/alpaca-gpt4-data-zh](https://huggingface.co/datasets/llm-wizard/alpaca-gpt4-data-zh)
|
45 |
+
|
46 |
+
**Usage and License Notices:**
|
47 |
+
The data is intended and licensed for research use only. The dataset is CC BY NC 4.0, allowing only non-commercial use. Models trained using this dataset should not be used outside of research purposes.
|
48 |
+
|
49 |
+
**Citation:**
|
50 |
+
```
|
51 |
+
@article{peng2023gpt4llm,
|
52 |
+
title={Instruction Tuning with GPT-4},
|
53 |
+
author={Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, Jianfeng Gao},
|
54 |
+
journal={arXiv preprint arXiv:2304.03277},
|
55 |
+
year={2023}
|
56 |
+
}
|
57 |
+
```
|
58 |
+
|
59 |
+
**许可证信息**
|
60 |
+
|
61 |
+
本项目的许可证由各集成工程的许可证构成:
|
62 |
+
|
63 |
+
1. **Meta-Llama3 项目**
|
64 |
+
- 项目地址:[https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
|
65 |
+
- 许可证:Llama 3 Community License Agreement
|
66 |
+
|
67 |
+
**引用说明:**
|
68 |
+
```
|
69 |
+
@article{llama3modelcard,
|
70 |
+
title={Llama 3 Model Card},
|
71 |
+
author={AI@Meta},
|
72 |
+
year={2024},
|
73 |
+
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
|
74 |
+
}
|
75 |
+
```
|
76 |
+
|
77 |
+
2. **Unsloth 项目**
|
78 |
+
- 许可证:Apache-2.0 许可证
|
79 |
+
- 项目地址:[https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit)
|
80 |
+
|
81 |
+
3. **中文数据集集成**
|
82 |
+
- 数据集:alpaca-gpt4-data-zh
|
83 |
+
- 许可证:CC BY NC 4.0(仅用于非商业的研究用途)
|
84 |
+
- 数据集地址:[https://huggingface.co/datasets/llm-wizard/alpaca-gpt4-data-zh](https://huggingface.co/datasets/llm-wizard/alpaca-gpt4-data-zh)
|
85 |
+
|
86 |
+
**使用和许可证通知:**
|
87 |
+
该数据仅限于研究使用,且基于 CC BY NC 4.0 许可证,只允许非商业用途。使用此数据集训练的模型不得用于研究用途以外的场合。
|
88 |
+
|
89 |
+
**引用说明:**
|
90 |
+
```
|
91 |
+
@article{peng2023gpt4llm,
|
92 |
+
title={Instruction Tuning with GPT-4},
|
93 |
+
author={Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, Jianfeng Gao},
|
94 |
+
journal={arXiv preprint arXiv:2304.03277},
|
95 |
+
year={2023}
|
96 |
+
}
|
97 |
+
```
|