FastFlowLM commited on
Commit
fd6822d
·
verified ·
1 Parent(s): 335ed5d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -23
README.md CHANGED
@@ -12,29 +12,6 @@ tags:
12
  - transformers
13
  ---
14
 
15
- # To Switch Between Thinking and Non-Thinking
16
- If you are using llama.cpp, Ollama, Open WebUI etc., you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
17
-
18
- Here is an example of multi-turn conversation:
19
-
20
- ```
21
- > Who are you /no_think
22
-
23
- <think>
24
-
25
- </think>
26
-
27
- I am Qwen, a large-scale language model developed by Alibaba Cloud. [...]
28
-
29
- > How many 'r's are in 'strawberries'? /think
30
-
31
- <think>
32
- Okay, let's see. The user is asking how many times the letter 'r' appears in the word "strawberries". [...]
33
- </think>
34
-
35
- The word strawberries contains 3 instances of the letter r. [...]
36
- ```
37
-
38
  # Qwen3-0.6B
39
 
40
  ## Qwen3 Highlights
 
12
  - transformers
13
  ---
14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  # Qwen3-0.6B
16
 
17
  ## Qwen3 Highlights