FastFlowLM commited on
Commit
e9c4eff
·
verified ·
1 Parent(s): 3bd01ec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -24
README.md CHANGED
@@ -7,33 +7,9 @@ license: apache-2.0
7
  tags:
8
  - qwen3
9
  - qwen
10
- - unsloth
11
  - transformers
12
  ---
13
 
14
- # To Switch Between Thinking and Non-Thinking
15
- 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.
16
-
17
- Here is an example of multi-turn conversation:
18
-
19
- ```
20
- > Who are you /no_think
21
-
22
- <think>
23
-
24
- </think>
25
-
26
- I am Qwen, a large-scale language model developed by Alibaba Cloud. [...]
27
-
28
- > How many 'r's are in 'strawberries'? /think
29
-
30
- <think>
31
- Okay, let's see. The user is asking how many times the letter 'r' appears in the word "strawberries". [...]
32
- </think>
33
-
34
- The word strawberries contains 3 instances of the letter r. [...]
35
- ```
36
-
37
  # Qwen3-8B
38
 
39
  ## Qwen3 Highlights
 
7
  tags:
8
  - qwen3
9
  - qwen
 
10
  - transformers
11
  ---
12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  # Qwen3-8B
14
 
15
  ## Qwen3 Highlights