huggingface/alignment-handbook Issues
Cannot flatten integer dtype tensors
Updated 1Question about sft with deepspeed
Updated 1Clarification on dataset mixer
Updated 5Missing config_qlora.yaml
Closed 2FSDP + QDoRA Support
Updated 6How to work with local data
Updated 1Using MT-Bench to evaluate zephyr
Updated 2(QLoRA) DPO without previous SFT
Updated 1Reward Modeling Support
Updatedhuggingface_hub version
Closed 1