Files

NanoCode012 8c3a727f9d feat: update yml chat_template to specify dataset field (#2001 ) [skip ci]

* feat: update yml chat_template to specify dataset field

* feat: replace sharegpt references with chat_template

2024-10-29 10:26:03 -04:00

lora-3.5.yaml

feat: update yml chat_template to specify dataset field (#2001 ) [skip ci]

2024-10-29 10:26:03 -04:00

phi2-ft.yml

update outputs path so that we can mount workspace to /workspace/data (#1623 )

2024-05-15 12:44:13 -04:00

phi3-ft-fsdp.yml

Create phi3-ft-fsdp.yml (#1580 )

2024-06-04 16:20:25 -04:00

phi3-ft.yml

Phi-3 conversation format, example training script and perplexity metric (#1582 )

2024-06-04 16:11:56 -04:00

phi-ft.yml

update outputs path so that we can mount workspace to /workspace/data (#1623 )

2024-05-15 12:44:13 -04:00

phi-qlora.yml

update outputs path so that we can mount workspace to /workspace/data (#1623 )

2024-05-15 12:44:13 -04:00

README.md

Mixtral fixes 20240124 (#1192 ) [skip ci]

2024-01-24 14:59:57 -05:00

README.md

Phi

Due to some nuances with the phi code, please use deepspeed when training phi for full finetune.

accelerate launch -m axolotl.cli.train examples/phi/phi-ft.yml --deepspeed deepspeed_configs/zero1.json

# OR

python -m axolotl.cli.train examples/phi/phi-qlora.yml