mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-06-04 13:19:43 +00:00
0f785cb1f3
* Add RoBERTa for RLHF Stage 2 & 3 (test) RoBERTa for RLHF Stage 2 & 3 (still in testing) Revert "Add RoBERTa for RLHF Stage 2 & 3 (test)" This reverts commit06741d894d. Add RoBERTa for RLHF stage 2 & 3 1. add roberta folder under model folder 2. add roberta option in train_reward_model.py 3. add some test in testci Update test_ci.sh Revert "Update test_ci.sh" This reverts commit 9c7352b81766f3177d31eeec0ec178a301df966a. Add RoBERTa for RLHF Stage 2 & 3 (test) RoBERTa for RLHF Stage 2 & 3 (still in testing) Revert "Add RoBERTa for RLHF Stage 2 & 3 (test)" This reverts commit06741d894d. Add RoBERTa for RLHF stage 2 & 3 1. add roberta folder under model folder 2. add roberta option in train_reward_model.py 3. add some test in testci Update test_ci.sh Revert "Update test_ci.sh" This reverts commit 9c7352b81766f3177d31eeec0ec178a301df966a. update roberta with coati chat ci update Revert "chat ci update" This reverts commit 17ae7ae01fa752bd3289fc39069868fde99cf846. * Update README.md Update README.md * update readme * Update test_ci.sh * update readme and add a script update readme and add a script modify readme Update README.md
12 lines
465 B
Python
12 lines
465 B
Python
jsonl_file = 'seed_prompts_xx.jsonl' # seed_prompts_en.jsonl or seed_prompts_ch.json from InstructionWild
|
|
reformat_file = 'prompts_xx.jsonl' # reformat jsonl file used as Prompt dataset in Stage3
|
|
|
|
data = ''
|
|
with open(jsonl_file, 'r', encoding="utf-8") as f1:
|
|
for jsonstr in f1.readlines():
|
|
jsonstr = '\t' + jsonstr.strip('\n') + ',\n'
|
|
data = data + jsonstr
|
|
data = '[\n' + data + ']'
|
|
|
|
with open(reformat_file, 'w') as f2:
|
|
f2.write(data) |