Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adding pointer back to Meta's LLaMA. #277

Merged
merged 1 commit into from
Apr 6, 2023
Merged

Adding pointer back to Meta's LLaMA. #277

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion examples/stack_llama/scripts/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# RLHF pipeline for the creation of Stack LLaMa" a Stack exchange llama-7b model.
# RLHF pipeline for the creation of StackLLaMa: a Stack exchange llama-7b model.
There were three main steps to the training process:
1. Supervised fine-tuning of the base llama-7b model to create llama-7b-se:
- `torchrun --nnodes 1 --nproc_per_node 8 examples/stack_llama/scripts/supervised_finetuning.py --model_path=<LLAMA_MODEL_PATH> --streaming --no_gradient_checkpointing --learning_rate 1e-5 --max_steps 5000 --output_dir ./llama-se`
Expand All @@ -13,3 +13,5 @@ At each stage the peft adapter layers were merged with the base model, using:
```shell
python merge_peft_adapter.py --model_id=XXX --base_model_id=YYY --output_name=ZZZ
```

For access to the base llama-7b model, please see Meta's [release](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) and [request form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform).