Update dataset_info.json

Added the Nectar dataset already preprocessed and divided in sft and rl to which I added a preprompt to each instruction since it has been seen that this increase instruction following
This commit is contained in:
Marco 2023-11-30 16:21:34 +01:00 committed by GitHub
parent 327d7f7efe
commit 9468ee9012
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 0 deletions

View File

@ -266,6 +266,12 @@
"columns": {
"prompt": "content"
}
"nectar_rlaif": {
"hf_hub_url": "mlinmg/RLAIF-Nectar",
"ranking": true
},
"nectar_sft": {
"hf_hub_url": "mlinmg/SFT-Nectar"
},
"starcoder": {
"hf_hub_url": "bigcode/starcoderdata",