From 34f44a53c0e286e561c0f241251910224d5f3f11 Mon Sep 17 00:00:00 2001 From: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com> Date: Thu, 11 Sep 2025 02:04:44 -0700 Subject: [PATCH] [Bug fix #40813] Fix base_model_tp_plan of Starcoder2 model. Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com> --- src/transformers/models/starcoder2/configuration_starcoder2.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/transformers/models/starcoder2/configuration_starcoder2.py b/src/transformers/models/starcoder2/configuration_starcoder2.py index 795fcb4696b8..a700b4f42548 100644 --- a/src/transformers/models/starcoder2/configuration_starcoder2.py +++ b/src/transformers/models/starcoder2/configuration_starcoder2.py @@ -141,7 +141,7 @@ class Starcoder2Config(PretrainedConfig): "layers.*.self_attn.v_proj": "colwise", "layers.*.self_attn.o_proj": "rowwise", "layers.*.mlp.c_fc": "colwise", - "layers.*.mlp.c_proj": "colwise", + "layers.*.mlp.c_proj": "rowwise", } base_model_pp_plan = { "embed_tokens": (["input_ids"], ["inputs_embeds"]),