Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,42 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: yentinglin/Llama-3-Taiwan-70B-Instruct
|
3 |
+
language:
|
4 |
+
- zh
|
5 |
+
- en
|
6 |
+
license: llama3
|
7 |
+
model_creator: yentinglin
|
8 |
+
model_name: Llama-3-Taiwan-70B-Instruct
|
9 |
+
model_type: llama
|
10 |
+
pipeline_tag: text-generation
|
11 |
+
quantized_by: minyichen
|
12 |
+
tags:
|
13 |
+
- llama-3
|
14 |
+
---
|
15 |
+
|
16 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/5df9c78eda6d0311fd3d541f/vlfv5sHbt4hBxb3YwULlU.png" alt="Taiwan LLM Logo" width="600" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
17 |
+
|
18 |
+
# Llama-3-Taiwan-70B-Instruct - GPTQ
|
19 |
+
- Model creator: [Yen-Ting Lin](https://huggingface.co/yentinglin)
|
20 |
+
- Original model: [Llama-3-Taiwan-70B-Instruct](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct)
|
21 |
+
|
22 |
+
<!-- description start -->
|
23 |
+
## Description
|
24 |
+
|
25 |
+
This repo contains GPTQ model files for [Llama-3-Taiwan-70B-Instruct](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct).
|
26 |
+
|
27 |
+
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
|
28 |
+
|
29 |
+
<!-- description end -->
|
30 |
+
<!-- repositories-available start -->
|
31 |
+
* [GPTQ models for GPU inference](minyichen/Llama-3-Taiwan-70B-Instruct-GPTQ)
|
32 |
+
* [Yen-Ting Lin's original unquantized model](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct)
|
33 |
+
<!-- repositories-available end -->
|
34 |
+
|
35 |
+
<!-- prompt-template start -->
|
36 |
+
## Prompt template: Vicuna
|
37 |
+
|
38 |
+
```
|
39 |
+
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: {prompt} ASSISTANT:
|
40 |
+
|
41 |
+
```
|
42 |
+
<!-- prompt-template end -->
|