lora modules: all by default

Former-commit-id: cae4737907
2025-12-14 19:06:26 +08:00 · 2024-06-06 03:53:28 +08:00
parent 679810a3d2
commit cceff9f520
23 changed files with 78 additions and 118 deletions
--- a/examples/lora_single_gpu/llama3_lora_dpo.yaml
+++ b/examples/lora_single_gpu/llama3_lora_dpo.yaml
@@ -5,7 +5,7 @@ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 stage: dpo
 do_train: true
 finetuning_type: lora
-lora_target: q_proj,v_proj
+lora_target: all
 pref_beta: 0.1
 pref_loss: sigmoid  # [sigmoid (dpo), orpo, simpo]

--- a/examples/lora_single_gpu/llama3_lora_kto.yaml
+++ b/examples/lora_single_gpu/llama3_lora_kto.yaml
@@ -5,7 +5,7 @@ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 stage: kto
 do_train: true
 finetuning_type: lora
-lora_target: q_proj,v_proj
+lora_target: all

 ### dataset
 dataset: kto_en_demo
--- a/examples/lora_single_gpu/llama3_lora_ppo.yaml
+++ b/examples/lora_single_gpu/llama3_lora_ppo.yaml
@@ -6,7 +6,7 @@ reward_model: saves/llama3-8b/lora/reward
 stage: ppo
 do_train: true
 finetuning_type: lora
-lora_target: q_proj,v_proj
+lora_target: all

 ### dataset
 dataset: identity,alpaca_en_demo
--- a/examples/lora_single_gpu/llama3_lora_pretrain.yaml
+++ b/examples/lora_single_gpu/llama3_lora_pretrain.yaml
@@ -5,7 +5,7 @@ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 stage: pt
 do_train: true
 finetuning_type: lora
-lora_target: q_proj,v_proj
+lora_target: all

 ### dataset
 dataset: c4_demo
--- a/examples/lora_single_gpu/llama3_lora_reward.yaml
+++ b/examples/lora_single_gpu/llama3_lora_reward.yaml
@@ -5,7 +5,7 @@ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 stage: rm
 do_train: true
 finetuning_type: lora
-lora_target: q_proj,v_proj
+lora_target: all

 ### dataset
 dataset: dpo_en_demo
--- a/examples/lora_single_gpu/llama3_lora_sft.yaml
+++ b/examples/lora_single_gpu/llama3_lora_sft.yaml
@@ -5,7 +5,7 @@ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 stage: sft
 do_train: true
 finetuning_type: lora
-lora_target: q_proj,v_proj
+lora_target: all

 ### dataset
 dataset: identity,alpaca_en_demo
--- a/examples/lora_single_gpu/llama3_preprocess.yaml
+++ b/examples/lora_single_gpu/llama3_preprocess.yaml
@@ -5,7 +5,7 @@ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 stage: sft
 do_train: true
 finetuning_type: lora
-lora_target: q_proj,v_proj
+lora_target: all

 ### dataset
 dataset: identity,alpaca_en_demo
--- a/examples/lora_single_gpu/llava1_5_lora_sft.yaml
+++ b/examples/lora_single_gpu/llava1_5_lora_sft.yaml
@@ -6,7 +6,7 @@ visual_inputs: true
 stage: sft
 do_train: true
 finetuning_type: lora
-lora_target: q_proj,v_proj
+lora_target: all

 ### dataset
 dataset: mllm_demo