Update README.md
Browse files
README.md
CHANGED
|
@@ -50,6 +50,8 @@ ALMA-7B-Ja(Ours) | 26.41/83.13 | 34.39/83.50 | 24.77/81.12 | 20.60/78.54 | 15.57
|
|
| 50 |
mmnga made llama.cpp(gguf) version [webbigdata-ALMA-7B-Ja-gguf](https://huggingface.co/mmnga/webbigdata-ALMA-7B-Ja-gguf). Thank you!
|
| 51 |
llama.cpp is a tool used primarily on Macs, and gguf is its latest version format. It can be used without gpu.
|
| 52 |
|
|
|
|
|
|
|
| 53 |
|
| 54 |
### ALMA-7B-Ja-GPTQ-Ja-En
|
| 55 |
GPTQ is quantized(reduce the size of the model) method and ALMA-7B-Ja-GPTQ has GPTQ quantized version that reduces model size(3.9GB) and memory usage.
|
|
|
|
| 50 |
mmnga made llama.cpp(gguf) version [webbigdata-ALMA-7B-Ja-gguf](https://huggingface.co/mmnga/webbigdata-ALMA-7B-Ja-gguf). Thank you!
|
| 51 |
llama.cpp is a tool used primarily on Macs, and gguf is its latest version format. It can be used without gpu.
|
| 52 |
|
| 53 |
+
[ALMA-7B-Ja-gguf Free Colab sample](https://github.com/webbigdata-jp/python_sample/blob/main/ALMA_7B_Ja_gguf_Free_Colab_sample.ipynb)
|
| 54 |
+
|
| 55 |
|
| 56 |
### ALMA-7B-Ja-GPTQ-Ja-En
|
| 57 |
GPTQ is quantized(reduce the size of the model) method and ALMA-7B-Ja-GPTQ has GPTQ quantized version that reduces model size(3.9GB) and memory usage.
|