Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,59 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- lianghsun/Llama-3.2-Taiwan-3B-Instruct
|
| 4 |
+
language:
|
| 5 |
+
- zh
|
| 6 |
+
- en
|
| 7 |
+
- ja
|
| 8 |
+
- ko
|
| 9 |
+
- fr
|
| 10 |
+
- it
|
| 11 |
+
- de
|
| 12 |
+
license: llama3.2
|
| 13 |
+
tags:
|
| 14 |
+
- ROC
|
| 15 |
+
- Taiwan
|
| 16 |
+
- zh-tw
|
| 17 |
+
- llama-factory
|
| 18 |
+
new_version: lianghsun/Llama-3.2-Taiwan-3B-Instruct
|
| 19 |
+
pipeline_tag: text-generation
|
| 20 |
+
library_name: llama.cpp
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
# Model Card for lianghsun/Llama-3.2-Taiwan-3B-Instruct-GGUF
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
<div align="center">圖像後製來自 <a href="https://online.visual-paradigm.com/">VisuaParadigm</a>：站在玉山上的量化 🦙 。
|
| 27 |
+
</div>
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
透過 [llama.cpp](https://github.com/ggerganov/llama.cpp) 將 [lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct) 版本轉成 `.gguf` 和各種量化版本模型。
|
| 31 |
+
|
| 32 |
+
<details>
|
| 33 |
+
<summary><b>Model Change Log</b></summary>
|
| 34 |
+
|
| 35 |
+
| Update Date | Model Version | Key Changes |
|
| 36 |
+
|--------------|-----------------------|-------------------------------------|
|
| 37 |
+
| 2025-01-01 | v2025.01.01 | This version corresponds to the `v2025.01.01` release of [lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct). |
|
| 38 |
+
| 2024-12-11 | v2024.12.11 | This version corresponds to the `v2024.11.27` release of [lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct). |
|
| 39 |
+
|
| 40 |
+
</details>
|
| 41 |
+
|
| 42 |
+
## More Information
|
| 43 |
+
|
| 44 |
+
請參考不同 tag 選擇對照的原始非量化的版本，最新的 main 分支對映的是 `v2025.01.01` 版本，有關原始非量化版本請參考原始模型 [lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct) 介紹。
|
| 45 |
+
|
| 46 |
+
**已知問題：** 量化後的模型會有機率輸出全部簡體中文的情況，此問題目前尚未深入研究原因。
|
| 47 |
+
|
| 48 |
+
### Issuses
|
| 49 |
+
#### How to use in Ollama
|
| 50 |
+
根據 [Issue：ollama 直接run gguf會跑出文不對題](https://discord.com/channels/1310544431983759450/1327811803085799534) 討論串， [@k1dave6412](https://huggingface.co/k1dave6412) 查出原因是要調整預設的對話模板（chat template），故我們在 repo 內有放置一個 `template` 的檔案來修正這個問題，但如果你要客制你的對話模板，請照著 Ollama 的 [Template](https://github.com/ollama/ollama/blob/main/docs/modelfile.md) 設定。
|
| 51 |
+
|
| 52 |
+
## Model Card Authors
|
| 53 |
+
|
| 54 |
+
[Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang)
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
## Model Card Contact
|
| 58 |
+
|
| 59 |
+
[Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang)
|