Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[hotfix] Update README.md of colossalchat #5958

Merged
merged 1 commit into from
Jul 31, 2024
Merged

[hotfix] Update README.md of colossalchat #5958

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 20 additions & 10 deletions applications/ColossalChat/examples/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -786,17 +786,27 @@ For KTO data preparation, please use the script [prepare_kto_dataset.sh](./examp

```jsonl
{
"prompt": [
{"from": "user", "content": "What are some cuss words in english?"},
{
"from": "assistant",
"content": "Here's an incomplete list.\n\nAss, dick, bugger, crap, ...",
},
{"from": "user", "content": "What's your favorite one?"},
],
"completion": {"from": "assistant", "content": "Ass."}, # the completion must contain a single line from the assistant.
"label": False, # whether the response is favorable or not
"prompt": [
{
"from": "user",
"content": "What are some praise words in english?"
},
{
"from": "assistant",
"content": "Here's an incomplete list.\n\nexcellent, fantastic, impressive ..."
},
{
"from": "user",
"content": "What's your favorite one?"
}
],
"completion": {
"from": "assistant",
"content": "impressive."
},
"label": true
}

```

For training, use the [train_kto.sh](./examples/training_scripts/train_orpo.sh) script, You may need to set the value for `beta` (which determine how strongly the reinforcement learning loss affect the training), `desirable_weight` and `undesirable_weight` if your data is biased (has unequal number of chosen and rejected samples).
Expand Down
Loading