File size: 378 Bytes
8f2f3c8
febe9a5
6017c5b
0bbda48
febe9a5
 
 
7a00638
 
 
1
2
3
4
5
6
7
8
9
10
11
# GGML 4-bit/5-bit quantized IDEA-CCNL/Ziya-LLaMA-13B-v1
* You need the latest version of llama-cpp or llama-cpp-python (to support ggml format v3).
* Currently llama-cmake can not tokenize '\<human\>', '\<bot\>' special tokens, I changed these to 🤖🧑 emojis.
  * Promote like this:
  ```python
  inputs = '🧑:' + query.strip() + '\n🤖:'
  ```
---
license: gpl-3.0
---