Update README.md
Browse files
README.md
CHANGED
@@ -10,6 +10,9 @@ datasets:
|
|
10 |
language:
|
11 |
- ja
|
12 |
- en
|
|
|
|
|
|
|
13 |
inference: false
|
14 |
---
|
15 |
|
@@ -23,6 +26,10 @@ We conduct continual pre-training of [meta-llama/Meta-Llama-3-8B](https://huggin
|
|
23 |
|
24 |
The name `youko` comes from the Japanese word [`ε¦η/γγγ/Youko`](https://ja.wikipedia.org/wiki/%E5%A6%96%E7%8B%90), which is a kind of Japanese mythical creature ([`ε¦ζͺ/γγγγ/Youkai`](https://ja.wikipedia.org/wiki/%E5%A6%96%E6%80%AA)).
|
25 |
|
|
|
|
|
|
|
|
|
26 |
|
27 |
* **Library**
|
28 |
|
@@ -45,6 +52,8 @@ The name `youko` comes from the Japanese word [`ε¦η/γγγ/Youko`](https:/
|
|
45 |
* **Contributors**
|
46 |
|
47 |
- [Koh Mitsuda](https://huggingface.co/mitsu-koh)
|
|
|
|
|
48 |
- [Kei Sawada](https://huggingface.co/keisawada)
|
49 |
|
50 |
---
|
@@ -79,7 +88,7 @@ print(output)
|
|
79 |
---
|
80 |
|
81 |
# Tokenization
|
82 |
-
The model uses the original meta-llama/Meta-Llama-3-8B tokenizer.
|
83 |
|
84 |
---
|
85 |
|
@@ -87,7 +96,7 @@ The model uses the original meta-llama/Meta-Llama-3-8B tokenizer.
|
|
87 |
```bibtex
|
88 |
@misc{rinna-llama-3-youko-8b,
|
89 |
title = {rinna/llama-3-youko-8b},
|
90 |
-
author = {Mitsuda, Koh and Sawada, Kei},
|
91 |
url = {https://huggingface.co/rinna/llama-3-youko-8b}
|
92 |
}
|
93 |
|
|
|
10 |
language:
|
11 |
- ja
|
12 |
- en
|
13 |
+
tags:
|
14 |
+
- llama
|
15 |
+
- llama-3
|
16 |
inference: false
|
17 |
---
|
18 |
|
|
|
26 |
|
27 |
The name `youko` comes from the Japanese word [`ε¦η/γγγ/Youko`](https://ja.wikipedia.org/wiki/%E5%A6%96%E7%8B%90), which is a kind of Japanese mythical creature ([`ε¦ζͺ/γγγγ/Youkai`](https://ja.wikipedia.org/wiki/%E5%A6%96%E6%80%AA)).
|
28 |
|
29 |
+
| Size | Continual Pre-Training | Instruction-Tuning |
|
30 |
+
| :- | :- | :- |
|
31 |
+
| 8B | Llama 3 Youko 8B [[HF]](https://huggingface.co/rinna/llama-3-youko-8b) [[GPTQ]](https://huggingface.co/rinna/llama-3-youko-8b-gptq) | Llama 3 Youko 8B Instruct [[HF]](https://huggingface.co/rinna/llama-3-youko-8b-instruct) [[GPTQ]](https://huggingface.co/rinna/llama-3-youko-8b-instruct-gptq) |
|
32 |
+
| 70B | Llama 3 Youko 70B [[HF]](https://huggingface.co/rinna/llama-3-youko-70b) [[GPTQ]](https://huggingface.co/rinna/llama-3-youko-70b-gptq) | Llama 3 Youko 70B Instruct [[HF]](https://huggingface.co/rinna/llama-3-youko-70b-instruct) [[GPTQ]](https://huggingface.co/rinna/llama-3-youko-70b-instruct-gptq) |
|
33 |
|
34 |
* **Library**
|
35 |
|
|
|
52 |
* **Contributors**
|
53 |
|
54 |
- [Koh Mitsuda](https://huggingface.co/mitsu-koh)
|
55 |
+
- [Xinqi Chen](https://huggingface.co/Keely0419)
|
56 |
+
- [Toshiaki Wakatsuki](https://huggingface.co/t-w)
|
57 |
- [Kei Sawada](https://huggingface.co/keisawada)
|
58 |
|
59 |
---
|
|
|
88 |
---
|
89 |
|
90 |
# Tokenization
|
91 |
+
The model uses the original [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) tokenizer.
|
92 |
|
93 |
---
|
94 |
|
|
|
96 |
```bibtex
|
97 |
@misc{rinna-llama-3-youko-8b,
|
98 |
title = {rinna/llama-3-youko-8b},
|
99 |
+
author = {Mitsuda, Koh and Chen, Xinqi and Wakatsuki, Toshiaki and Sawada, Kei},
|
100 |
url = {https://huggingface.co/rinna/llama-3-youko-8b}
|
101 |
}
|
102 |
|