deepspeedai / deepspeedai/DeepSpeedExamples
RLHF model return '{: {: {:' of every input
Open
Nobody has claimed this yet.
deespeed chat
modeling
- Dominant language
- Python
- Stars
- 6.8k
- Forks
- 1.1k
- Avg merge
- 2d 16h
- Merged PRs (30d)
- 1
Description
I used as readme of deepspeed chat.
training/step1_supervised_finetuning/training_scripts/single_node/run_1.3b.sh
training/step2_reward_model_finetuning/training_scripts/single_node/run_350m.sh
training/step3_rlhf_finetuning/training_scripts/single_node/run_1.3b.sh
python3 chat.py --path output/step3-models/1.3b/actor
bug when i want to try chat.py . the result is :
Enter input (type 'quit' to exit, 'clear' to clean memory): What is Edge?
------------------------------ Round 1 ------------------------------
Human: What is Edge?
Assistant: {: {: {: {: {: {: {: {: {: {:
Enter input (type 'quit' to exit, 'clear' to clean memory): clear
Enter input (type 'quit' to exit, 'clear' to clean memory): hello
------------------------------ Round 1 ------------------------------
Human: hello
Assistant: {: {: {: {: {: {: {: {: {: {: {: {: {:
Enter input (type 'quit' to exit, 'clear' to clean memory): clear
Enter input (type 'quit' to exit, 'clear' to clean memory): who are you?
------------------------------ Round 1 ------------------------------
Human: who are you?
Assistant: {: {: {: {: {: {: {: {: {: {:
Enter input (type 'quit' to exit, 'clear' to clean memory):
every inputs it returns "{: {: {: {: {: {: {: {: {: {:" .
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.