wassname/alignment-handbook
1
0
Fork 0
mirror of https://github.com/wassname/alignment-handbook.git synced 2026-07-25 13:00:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Resolves #13 fix typo in zephyr recipe readme

Browse Source
This commit is contained in:
Sebastian Schramm
2023-11-10 16:57:39 +01:00
parent e4f98e7d8f
commit d48a4a477b
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
recipes/zephyr-7b-beta/README.md
+2 -2
View File
@@ -15,14 +15,14 @@ See below for commands to train these models using either DeepSpeed ZeRO-3 or Lo
ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_sft.py recipes/zephyr-7b-beta/sft/config_full.yaml
# Step 2 - DPO
ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_dpo.py recipes/zephyr-7b-beta/beta/beta/beta/dpo/config_full.yaml
ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_dpo.py recipes/zephyr-7b-beta/dpo/config_full.yaml
```
## LoRA training examples
```shell
# Step 1 - SFT
ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=1 scripts/run_sft.py recipes/zephyr-7b-beta/beta/sft/config_lora.yaml
ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=1 scripts/run_sft.py recipes/zephyr-7b-beta/sft/config_lora.yaml
# Step 2 - DPO
ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=1 scripts/run_dpo.py recipes/zephyr-7b-beta/dpo/config_lora.yaml