Updated README.md for branches description.
Browse files
README.md
CHANGED
|
@@ -29,6 +29,20 @@ Original model 原始模型: https://huggingface.co/yentinglin/Taiwan-LLM-13B-v2
|
|
| 29 |
|
| 30 |
This is a quantizated model from [yentinglin/Taiwan-LLM-13B-v2.0-chat](https://huggingface.co/yentinglin/Taiwan-LLM-13B-v2.0-chat) in exl2 format.
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
## Citation
|
| 33 |
|
| 34 |
If you find Taiwan LLM is useful in your work, please cite it with:
|
|
|
|
| 29 |
|
| 30 |
This is a quantizated model from [yentinglin/Taiwan-LLM-13B-v2.0-chat](https://huggingface.co/yentinglin/Taiwan-LLM-13B-v2.0-chat) in exl2 format.
|
| 31 |
|
| 32 |
+
You are currently at the [main](https://huggingface.co/kennylam/Taiwan-LLM-13B-v2.0-chat-exl2/tree/main) branch, which provides only [measurement.json](measurement.json) used in the ExLlamaV2 quantization. Please take a look of your choices in following table of branches.
|
| 33 |
+
|
| 34 |
+
這裡是main branch, 只提供EvLlamaV2量化時所用到的[measurement.json](measurement.json)檔案。
|
| 35 |
+
|
| 36 |
+
[8.0bpw-h8](/kennylam/Taiwan-LLM-13B-v2.0-chat-exl2/tree/8.0bpw-h8) 8 bits per weight.
|
| 37 |
+
|
| 38 |
+
[6.0bpw-h6](/kennylam/Taiwan-LLM-13B-v2.0-chat-exl2/tree/6.0bpw-h6) 6 bits per weight.
|
| 39 |
+
|
| 40 |
+
[4.0bpw-h6](/kennylam/Taiwan-LLM-13B-v2.0-chat-exl2/tree/4.0bpw-h6) 4 bits per weight.
|
| 41 |
+
|
| 42 |
+
[3.0bpw-h6](/kennylam/Taiwan-LLM-13B-v2.0-chat-exl2/tree/3.0bpw-h6) 3 bits per weight.
|
| 43 |
+
|
| 44 |
+
[2.0bpw-h6](/kennylam/Taiwan-LLM-13B-v2.0-chat-exl2/tree/2.0bpw-h6) 2 bits per weight.
|
| 45 |
+
|
| 46 |
## Citation
|
| 47 |
|
| 48 |
If you find Taiwan LLM is useful in your work, please cite it with:
|