metadata
license: mit
base_model: JEJUMA/JEJUMA-002
tags:
- gguf
- Dialect
- Language
model-index:
- name: joongi007/JEJUMA-002-GGUF
results: []
language:
- ko
pipeline_tag: text-generation
Original model is JEJUMA/JEJUMA-002 - bbd7ec2
JEJUMA Official Quantization is JEJUMA/JEJUMA-002-GGUF
After trying out this model, I noticed a few things:
- It's more like a translation model. You can't chat with it, it only does translations.
- It can only handle one dialect (or standard Korean) at a time.
- Don't expect a conversation. It's strictly for translation purposes! Look at the example below!
system prompt
user questionAnswer your questions using the Jeju dialect.
assistant answerhello! How are you doing now?
헐쯤 험과게 # 할수 많습니까
Prompt(LM Studio)
<|start_header_id|>system<|end_header_id|>
{System}
<|eot_id|><|start_header_id|>user<|end_header_id|>
{User}
<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{Assistant}
Example of User Prompts
Detect the following sentence or word is standard, jeju, chungcheong, gangwon, gyeongsang, or jeonla's dialect:
```
{Enter the Jeju island dialect or standard Korean here}
```
Detect the following sentence or word is which dialect and convert the following sentence or word to standard Korean:
```
{Enter Jeju island dialect or standard Korean here}
```