github
/
ColossalAI
mirror of https://github.com/hpcaitech/ColossalAI
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

[doc] Fix typo s/infered/inferred/ (#5288) 

Signed-off-by: hugo-syn <hugo.vincent@synacktiv.com>
pull/5429/head
hugo-syn 9 months ago committed by GitHub
parent
5e1c93d732
commit
c8003d463b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 6
      applications/ColossalQA/colossalqa/prompt/README.md

6
applications/ColossalQA/colossalqa/prompt/README.md
Unescape View File

@ -24,7 +24,7 @@ Assistant:
### English ### English
``` ```
[INST] <<SYS>>Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. [INST] <<SYS>>Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If the answer cannot be infered based on the given context, please don't share false information.<</SYS>> If the answer cannot be inferred based on the given context, please don't share false information.<</SYS>>
Use the context and chat history to respond to the human's input at the end or carry on the conversation. You should generate one response only. No following up is needed. Use the context and chat history to respond to the human's input at the end or carry on the conversation. You should generate one response only. No following up is needed.
context: context:
@ -51,7 +51,7 @@ Note that the "[INST] <<SYS>>...<</SYS>>" template is the specific prompt format
#### Normal Length #### Normal Length
``` ```
[INST] <<SYS>>Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. [INST] <<SYS>>Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If the answer cannot be infered based on the given context, please don't share false information.<</SYS>> If the answer cannot be inferred based on the given context, please don't share false information.<</SYS>>
Use the context and chat history to respond to the human's input at the end or carry on the conversation. You should generate one response only. No following up is needed. Use the context and chat history to respond to the human's input at the end or carry on the conversation. You should generate one response only. No following up is needed.
context: context:
@ -73,7 +73,7 @@ Assistant:
#### Overlength #### Overlength
``` ```
[INST] <<SYS>>Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. [INST] <<SYS>>Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If the answer cannot be infered based on the given context, please don't share false information.<</SYS>> If the answer cannot be inferred based on the given context, please don't share false information.<</SYS>>
Use the context and chat history to respond to the human's input at the end or carry on the conversation. You should generate one response only. No following up is needed. Use the context and chat history to respond to the human's input at the end or carry on the conversation. You should generate one response only. No following up is needed.
context: context:

Write Preview
Loading…
Cancel
Save