xiaol commited on
Commit
061a077
1 Parent(s): 64f8ac4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -15,6 +15,8 @@ finetuned with ultrachat , COT and some novel instructions data, commitpackft an
15
 
16
  use full ultrachat and cot data, about 3B tokens
17
 
 
 
18
 
19
  # Contributor
20
  [@JL-er](https://huggingface.co/JL-er)
@@ -26,7 +28,7 @@ this model lose multi-turn chat ability,cause from using whole ultrachat dataset
26
 
27
  so i continue tuned multi-turn datasets with 2 aspects
28
 
29
- 1.role play
30
 
31
  2.for novel multiturn instruction
32
 
 
15
 
16
  use full ultrachat and cot data, about 3B tokens
17
 
18
+ if you wanna do Role play, use [this model](https://huggingface.co/xiaol/RWKV-4-world-one-state-ultrachat-COT-65k/blob/main/RWKV-world-novel-one-state-ultrachat-cot-tuned-Role-play-65k.pth)
19
+
20
 
21
  # Contributor
22
  [@JL-er](https://huggingface.co/JL-er)
 
28
 
29
  so i continue tuned multi-turn datasets with 2 aspects
30
 
31
+ 1.[role play](https://huggingface.co/xiaol/RWKV-4-world-one-state-ultrachat-COT-65k/blob/main/RWKV-world-novel-one-state-ultrachat-cot-tuned-Role-play-65k.pth)
32
 
33
  2.for novel multiturn instruction
34