Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,63 @@
|
|
1 |
-
---
|
2 |
-
license: llama3
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- ja
|
6 |
+
base_model:
|
7 |
+
- elyza/Llama-3-ELYZA-JP-8B
|
8 |
+
- rinna/llama-3-youko-8b-instruct
|
9 |
+
- lightblue/suzume-llama-3-8B-japanese
|
10 |
+
- neoai-inc/Llama-3-neoAI-8B-Chat-v0.1
|
11 |
+
- AXCXEPT/Llama-3-EZO-8b-Common-it
|
12 |
+
- tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
|
13 |
+
- alfredplpl/Llama-3-8B-Instruct-Ja
|
14 |
+
- haqishen/Llama-3-8B-Japanese-Instruct
|
15 |
+
- owner203/japanese-llama-3-8b-instruct-v2
|
16 |
+
- shisa-ai/shisa-v1-llama3-8b
|
17 |
+
library_name: transformers
|
18 |
+
tags:
|
19 |
+
- mergekit
|
20 |
+
- merge
|
21 |
+
---
|
22 |
+
# Llama3-ja
|
23 |
+
|
24 |
+
## Model Details
|
25 |
+
|
26 |
+
This model is a linear merge of multiple Llama 3 8B models fine-tuned for Japanese language tasks, created using [mergekit](https://github.com/cg123/mergekit).
|
27 |
+
The aim is to create a more robust and versatile Japanese language model that leverages the strengths of each individual model.
|
28 |
+
|
29 |
+
## Intended Use
|
30 |
+
|
31 |
+
This model is designed for various Japanese natural language processing tasks, including but not limited to:
|
32 |
+
|
33 |
+
- Text generation
|
34 |
+
- Conversation and chatbot applications
|
35 |
+
- Text completion
|
36 |
+
- Question answering
|
37 |
+
- Summarization
|
38 |
+
|
39 |
+
## Limitations
|
40 |
+
|
41 |
+
While this model combines multiple Japanese-focused Llama 3 models, it may still have limitations:
|
42 |
+
|
43 |
+
- Performance on specific tasks may vary
|
44 |
+
- The model may inherit biases from its constituent models
|
45 |
+
|
46 |
+
## Included models
|
47 |
+
|
48 |
+
By combining these models, we aim to create a more robust and versatile Japanese language model that leverages the strengths of each individual model.
|
49 |
+
|
50 |
+
- [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B)
|
51 |
+
- [rinna/llama-3-youko-8b-instruct](https://huggingface.co/rinna/llama-3-youko-8b-instruct)
|
52 |
+
- [lightblue/suzume-llama-3-8B-japanese](https://huggingface.co/lightblue/suzume-llama-3-8B-japanese)
|
53 |
+
- [neoai-inc/Llama-3-neoAI-8B-Chat-v0.1](https://huggingface.co/neoai-inc/Llama-3-neoAI-8B-Chat-v0.1)
|
54 |
+
- [AXCXEPT/Llama-3-EZO-8b-Common-it](https://huggingface.co/AXCXEPT/Llama-3-EZO-8b-Common-it)
|
55 |
+
- [tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1)
|
56 |
+
- [alfredplpl/Llama-3-8B-Instruct-Ja](https://huggingface.co/alfredplpl/Llama-3-8B-Instruct-Ja)
|
57 |
+
- [haqishen/Llama-3-8B-Japanese-Instruct](https://huggingface.co/haqishen/Llama-3-8B-Japanese-Instruct)
|
58 |
+
- [owner203/japanese-llama-3-8b-instruct-v2](https://huggingface.co/owner203/japanese-llama-3-8b-instruct-v2)
|
59 |
+
- [shisa-ai/shisa-v1-llama3-8b](https://huggingface.co/shisa-ai/shisa-v1-llama3-8b)
|
60 |
+
|
61 |
+
## Acknowledgements
|
62 |
+
|
63 |
+
Thank you to the creators and contributors of all the component models for their valuable work in advancing Japanese language AI capabilities.
|