DehydratedWater42 commited on
Commit
a8a68d4
1 Parent(s): 1b256a9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -37,7 +37,7 @@ The purpose of this model is to extract semantic relations from text in a struct
37
  ### Template:
38
  Use the **prompt template** provided below to extract relations from text. Replace `<<your_text_for_extraction>>` with your selected text, ideally between 500-1500 tokens,
39
  with an **optimal range** of about **800-1000 tokens**. You can adjust the **temperature** between 0.3 and 1.0; a good starting point is **between 0.6 and 0.7**.
40
- Temperatures below 0.5 may lead to never ending `section_description`. The higher the temperature, the more the model will fill in the gaps in the provided text.
41
  It was **fine-tuned on scientific articles**, so it will supplement missing information with general knowledge.
42
  Model was trained on 2560 context lenght where 1000-1500 tokens where used as input text.
43
 
 
37
  ### Template:
38
  Use the **prompt template** provided below to extract relations from text. Replace `<<your_text_for_extraction>>` with your selected text, ideally between 500-1500 tokens,
39
  with an **optimal range** of about **800-1000 tokens**. You can adjust the **temperature** between 0.3 and 1.0; a good starting point is **between 0.6 and 0.7**.
40
+ Temperatures below 0.3 may lead to never ending `section_description`. The higher the temperature, the more the model will fill in the gaps in the provided text.
41
  It was **fine-tuned on scientific articles**, so it will supplement missing information with general knowledge.
42
  Model was trained on 2560 context lenght where 1000-1500 tokens where used as input text.
43