Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,29 @@ tags:
|
|
| 7 |
- chatglm
|
| 8 |
- ggml
|
| 9 |
---
|
| 10 |
-
# ChatGLM3-6B-int4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
- chatglm
|
| 8 |
- ggml
|
| 9 |
---
|
| 10 |
+
# ChatGLM3-6B-int4
|
| 11 |
+
|
| 12 |
+
介绍 (Introduction)
|
| 13 |
+
ChatGLM3-6B 是 ChatGLM 系列最新一代的开源模型,[THUDM/chatglm3-6b](https://huggingface.co/THUDM/chatglm3-6b)
|
| 14 |
+
|
| 15 |
+
用 [ChatGLM.CPP]() 基於 GGML quantize 生成 Q4_0、Q4_1 權重 weights 儲存於此倉庫。
|
| 16 |
+
|
| 17 |
+
## Use in Python
|
| 18 |
+
1. Install dependency
|
| 19 |
+
```sh
|
| 20 |
+
pip install chatglm-cpp transformers
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
2. Download weight
|
| 24 |
+
```sh
|
| 25 |
+
wget https://huggingface.co/npc0/chatglm3-6b-int4/resolve/main/chatglm3-ggml-q4_0.bin
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
3. Code
|
| 29 |
+
```py
|
| 30 |
+
import chatglm_cpp
|
| 31 |
+
|
| 32 |
+
pipeline = chatglm_cpp.Pipeline("./chatglm3-ggml-q4_0.bin")
|
| 33 |
+
pipeline.chat(["你好"])
|
| 34 |
+
# Output: 你好👋!我是人工智能助手 ChatGLM3-6B,很高兴见到你,欢迎问我任何问题。
|
| 35 |
+
```
|