Update README.md
Browse files
README.md
CHANGED
@@ -8,13 +8,16 @@ This model quantized from openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf to
|
|
8 |
Reference :
|
9 |
- https://huggingface.co/openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf
|
10 |
- https://github.com/ggerganov/llama.cpp#prepare-data--run
|
|
|
|
|
|
|
11 |
|
12 |
Example run inference in colab.
|
13 |
```
|
14 |
# Download GUFF model from file and version.
|
15 |
!git clone https://github.com/ggerganov/llama.cpp.git
|
16 |
!pip install -r llama.cpp/requirements.txt
|
17 |
-
!./llama.cpp/main -m
|
18 |
|
19 |
#result example
|
20 |
#ยกตัวอย่างอาหารไทย สัก 5 ตัวอย่างมาแนะนำ
|
|
|
8 |
Reference :
|
9 |
- https://huggingface.co/openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf
|
10 |
- https://github.com/ggerganov/llama.cpp#prepare-data--run
|
11 |
+
|
12 |
+
How to quantize GUFF format:
|
13 |
+
https://colab.research.google.com/drive/1uI6Zsgcj-_KFhk3cX3xEbCdVVuIofVwA?usp=sharing
|
14 |
|
15 |
Example run inference in colab.
|
16 |
```
|
17 |
# Download GUFF model from file and version.
|
18 |
!git clone https://github.com/ggerganov/llama.cpp.git
|
19 |
!pip install -r llama.cpp/requirements.txt
|
20 |
+
!./llama.cpp/main -m openthaigpt-1.0.0-beta-7b-chat-ckpt-hf.gguf.Q4_0.bin -p "ยกตัวอย่างอาหารไทย สัก 5 ตัวอย่าง" -n 400 -e
|
21 |
|
22 |
#result example
|
23 |
#ยกตัวอย่างอาหารไทย สัก 5 ตัวอย่างมาแนะนำ
|