Update README.md
Browse files
README.md
CHANGED
@@ -21,9 +21,9 @@ library_name: transformers
|
|
21 |
|
22 |
# AKALLAMA
|
23 |
|
24 |
-
|
25 |
-
It
|
26 |
-
|
27 |
|
28 |
### Model Description
|
29 |
|
@@ -98,7 +98,42 @@ Detailed descriptions regarding training data will be announced later.
|
|
98 |
|
99 |
### Examples
|
100 |
|
101 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
102 |
|
103 |
## Special Thanks
|
104 |
|
|
|
21 |
|
22 |
# AKALLAMA
|
23 |
|
24 |
+
AkaLlama is a series of Korean language models designed for practical usability across a wide range of tasks.
|
25 |
+
The initial model, AkaLlama-v0.1, is a fine-tuned version of Meta-Llama-3-70b-Instruct. It has been trained on a custom mix of publicly available datasets curated by the MIR Lab.
|
26 |
+
Our goal is to explore cost-effective ways to adapt high-performing LLMs for specific use cases, such as different languages (e.g., Korean) or domains (e.g., organization-specific chatbots).
|
27 |
|
28 |
### Model Description
|
29 |
|
|
|
98 |
|
99 |
### Examples
|
100 |
|
101 |
+
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
|
102 |
+
<img src="https://github.com/0110tpwls/project/blob/master/image (8).png?raw=true" width="60%"/>
|
103 |
+
</a>
|
104 |
+
|
105 |
+
<details>
|
106 |
+
<summary><b>Math Solving[CLICK TO EXPAND]</b></summary>
|
107 |
+
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
|
108 |
+
<img src="https://github.com/0110tpwls/project/blob/master/image (9).png?raw=true" width="60%"/>
|
109 |
+
</a>
|
110 |
+
</details>
|
111 |
+
|
112 |
+
<details>
|
113 |
+
<summary><b>Writting[CLICK TO EXPAND]</b></summary>
|
114 |
+
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
|
115 |
+
<img src="https://github.com/0110tpwls/project/blob/master/image (13).png?raw=true" width="60%"/>
|
116 |
+
</a>
|
117 |
+
|
118 |
+
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
|
119 |
+
<img src="https://github.com/0110tpwls/project/blob/master/image (7).png?raw=true" width="60%"/>
|
120 |
+
</a>
|
121 |
+
</details>
|
122 |
+
|
123 |
+
<details>
|
124 |
+
<summary><b>logical Reasoning[CLICK TO EXPAND]</b></summary>
|
125 |
+
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
|
126 |
+
<img src="https://github.com/0110tpwls/project/blob/master/image (15).png?raw=true" width="60%"/>
|
127 |
+
</a>
|
128 |
+
</details>
|
129 |
+
|
130 |
+
<details>
|
131 |
+
<summary><b>Coding [CLICK TO EXPAND]</b></summary>
|
132 |
+
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
|
133 |
+
<img src="https://github.com/0110tpwls/project/blob/master/image (11).png?raw=true" width="60%"/>
|
134 |
+
</a>
|
135 |
+
</details>
|
136 |
+
You can find more examples at [our project page](https://yonsei-mir.github.io/AkaLLaMA-page/)
|
137 |
|
138 |
## Special Thanks
|
139 |
|