Hugging Face's logo

lemonilia
/
LimaRP-Llama2-7B-v3-EXPERIMENT

Model card Files Community
lemonilia commited on
Commit
787e4a2
•
1 Parent(s): cb889ba

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -4,7 +4,7 @@ license: apache-2.0
4
 
5
  # LimaRP-Llama2-7B-v3 (Alpaca, experimental, 4-bit LoRA adapter)
6
 
7
- This is an experimental version of LimaRP for Llama2, using a somewhat updated dataset (1800 training samples)
8
  and a 2-pass training procedure. The first pass includes unsupervised tuning on 2800 stories within
9
  4k tokens length and the second pass is LimaRP with changes introducing more effective control on bot response length.
10
 
 
4
 
5
  # LimaRP-Llama2-7B-v3 (Alpaca, experimental, 4-bit LoRA adapter)
6
 
7
+ This is an experimental version of LimaRP for Llama2 with an updated dataset (1800 training samples)
8
  and a 2-pass training procedure. The first pass includes unsupervised tuning on 2800 stories within
9
  4k tokens length and the second pass is LimaRP with changes introducing more effective control on bot response length.
10