Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -8,9 +8,9 @@ pinned: false
|
|
8 |
---
|
9 |
|
10 |
### KONI: KISTI Open Natural Intelligence
|
11 |
-
|
12 |
Our contributions include various language models and datasets aimed at advancing Korean natural language processing (NLP) techniques and utilizing science and technology information.
|
13 |
-
By providing these resources,
|
14 |
### NEWS
|
15 |
- [2024.12.10] ScienceON will begin providing an AI-reviewer service using KONI LLM that provides various analysis functions including understanding multiple scientific papers at once, comparing papers, summarizing papers, identifying limitations and differences, and conducting free Q&As. Please visit ScienceON to check how it works (https://scienceon.kisti.re.kr).
|
16 |
- [2024.11.15] KONI-Llama3.1-70B-Instruct model released with LogicKor Benchmark Score 9.38/10.
|
|
|
8 |
---
|
9 |
|
10 |
### KONI: KISTI Open Natural Intelligence
|
11 |
+
KONI is the representitive name for LLMs and LLM-based techniques developed by Large-scale AI Research Group at KISTI(Korea Institute of Science and Technolgy Information) that focuses on developing and sharing Korean models and datasets.
|
12 |
Our contributions include various language models and datasets aimed at advancing Korean natural language processing (NLP) techniques and utilizing science and technology information.
|
13 |
+
By providing these resources, KONI supports researchers and developers to create AI-based applications that effectively understand, analyze and generate Korean Scientific texts.
|
14 |
### NEWS
|
15 |
- [2024.12.10] ScienceON will begin providing an AI-reviewer service using KONI LLM that provides various analysis functions including understanding multiple scientific papers at once, comparing papers, summarizing papers, identifying limitations and differences, and conducting free Q&As. Please visit ScienceON to check how it works (https://scienceon.kisti.re.kr).
|
16 |
- [2024.11.15] KONI-Llama3.1-70B-Instruct model released with LogicKor Benchmark Score 9.38/10.
|