YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
!deepspeed --module openrlhf.cli.train_dpo
--save_path '/mnt/nvme1/will/1_dpo'
--save_steps 1024
--logging_steps 10
--eval_steps -1
--train_batch_size 256
--micro_train_batch_size 1
--pretrain 'mistralai/Mistral-Nemo-Instruct-2407'
--bf16
--max_epochs 1
--max_len 2048
--zero_stage 3
--learning_rate 5e-7
--dataset '/mnt/nvme1/will/2_dpo'
--apply_chat_template
--chosen_key chosen
--rejected_key rejected
--flash_attn
--gradient_checkpointing
- Downloads last month
- 10
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.