From 08bca186394d1e5bac532893eb7aa4a3dbcd0343 Mon Sep 17 00:00:00 2001 From: Sahil Jain Date: Fri, 21 Mar 2025 04:41:46 -0700 Subject: [PATCH 1/2] micro doc update with helpful reminder Signed-off-by: Sahil Jain --- docs/guides/grpo.md | 1 + docs/guides/sft.md | 1 + 2 files changed, 2 insertions(+) diff --git a/docs/guides/grpo.md b/docs/guides/grpo.md index 8d93fb64f7..b9ee746444 100644 --- a/docs/guides/grpo.md +++ b/docs/guides/grpo.md @@ -9,6 +9,7 @@ We recommend launching the job using `uv`: uv run examples/run_grpo_math.py --config {overrides} ``` If not specified, `config` will default to [examples/configs/grpo.yaml](../../examples/configs/grpo.yaml) +**Reminder**: Don't forget to set your HUGGINGFACE_TOKEN, HF_HOME, and WANDB_API_KEY (if needed) ## Now, for the details: diff --git a/docs/guides/sft.md b/docs/guides/sft.md index d994967bd2..ba29e88e04 100644 --- a/docs/guides/sft.md +++ b/docs/guides/sft.md @@ -21,6 +21,7 @@ uv run examples/run_sft.py \ cluster.gpus_per_node=1 \ logger.wandb.name="sft-dev-1-gpu" ``` +**Reminder**: Don't forget to set your HUGGINGFACE_TOKEN, HF_HOME, and WANDB_API_KEY (if needed) ## Datasets From a90476fc81a1279b5979bc2c3bce0591c9f8a7b0 Mon Sep 17 00:00:00 2001 From: Sahil Jain Date: Fri, 21 Mar 2025 04:50:48 -0700 Subject: [PATCH 2/2] micro doc update with helpful reminder Signed-off-by: Sahil Jain --- docs/guides/grpo.md | 3 ++- docs/guides/sft.md | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/guides/grpo.md b/docs/guides/grpo.md index b9ee746444..6ace84876d 100644 --- a/docs/guides/grpo.md +++ b/docs/guides/grpo.md @@ -9,7 +9,8 @@ We recommend launching the job using `uv`: uv run examples/run_grpo_math.py --config {overrides} ``` If not specified, `config` will default to [examples/configs/grpo.yaml](../../examples/configs/grpo.yaml) -**Reminder**: Don't forget to set your HUGGINGFACE_TOKEN, HF_HOME, and WANDB_API_KEY (if needed) + +**Reminder**: Don't forget to set your HF_HOME and WANDB_API_KEY (if needed). You'll need to do a `huggingface-cli login` as well for Llama models. ## Now, for the details: diff --git a/docs/guides/sft.md b/docs/guides/sft.md index ba29e88e04..4d452b109d 100644 --- a/docs/guides/sft.md +++ b/docs/guides/sft.md @@ -21,7 +21,7 @@ uv run examples/run_sft.py \ cluster.gpus_per_node=1 \ logger.wandb.name="sft-dev-1-gpu" ``` -**Reminder**: Don't forget to set your HUGGINGFACE_TOKEN, HF_HOME, and WANDB_API_KEY (if needed) +**Reminder**: Don't forget to set your HF_HOME and WANDB_API_KEY (if needed). You'll need to do a `huggingface-cli login` as well for Llama models. ## Datasets