47 lines
1.2 KiB
Markdown
47 lines
1.2 KiB
Markdown
---
|
|
language:
|
|
- ko
|
|
- en
|
|
license: apache-2.0
|
|
tags:
|
|
- text-generation
|
|
- qwen2.5
|
|
- korean
|
|
- instruct
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
## 📌 Notice
|
|
- ✅ Original model is [beomi/Qwen2.5-7B-Instruct-kowiki-qa](https://huggingface.co/beomi/Qwen2.5-7B-Instruct-kowiki-qa)
|
|
- ✅ Quantized by [teddylee777](https://huggingface.co/teddylee777) by using [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
|
|
|
## 💬 Template
|
|
|
|
```
|
|
FROM Qwen2.5-7B-Instruct-kowiki-qa-Q8_0.gguf
|
|
|
|
TEMPLATE """{{- if .System }}
|
|
<|im_start|>system
|
|
{{ .System }}
|
|
<|im_end|>
|
|
{{- end }}
|
|
<|im_start|>user
|
|
{{ .Prompt }}
|
|
<|im_end|>
|
|
<|im_start|>assistant
|
|
"""
|
|
|
|
SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant. 모든 대답은 한국어로 해주세요."""
|
|
|
|
PARAMETER temperature 0
|
|
PARAMETER num_ctx 128000
|
|
PARAMETER stop <|im_start|>
|
|
PARAMETER stop <|im_end|>
|
|
```
|
|
|
|
## 🧑💻 Helpful Contents
|
|
- ✅ [How to load HuggingFace GGUF into LM Studio](https://youtu.be/bANQk--Maxs)
|
|
- ✅ [How to test llama3 by using Ollama](https://youtu.be/12CuUQIPdM4)
|
|
- 🇰🇷 [LangChain Tutorial in Korean](https://wikidocs.net/book/14314)
|
|
- 🔥 Please subscribe and support on [YouTube](https://www.youtube.com/@teddynote)
|