[release] Bye 2025 (#9702)

examples/train_lora/deepseek2_lora_sft_kt.yaml

@@ -1,52 +0,0 @@
-### model
-model_name_or_path: deepseek-ai/DeepSeek-V2-Lite
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: identity
-template: deepseek
-cutoff_len: 2048
-max_samples: 100000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/Kllama_deepseekV2
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-save_only_model: false
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 8
-learning_rate: 1.0e-4
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-resume_from_checkpoint: null
-
-### ktransformers
-use_kt: true # use KTransformers as LoRA sft backend
-kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V2-Lite-Chat-sft-amx.yaml
-cpu_infer: 32
-chunk_size: 8192
-
-### eval
-# eval_dataset: alpaca_en_demo
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/deepseek3_lora_sft_kt.yaml

@@ -1,52 +0,0 @@
-### model
-model_name_or_path: opensourcerelease/DeepSeek-V3-bf16
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: identity
-template: deepseek
-cutoff_len: 2048
-max_samples: 100000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/Kllama_deepseekV3
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-save_only_model: false
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 8
-learning_rate: 1.0e-4
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-resume_from_checkpoint: null
-
-### ktransformers
-use_kt: true # use KTransformers as LoRA sft backend
-kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V3-Chat-sft-amx-multi-gpu.yaml
-cpu_infer: 32
-chunk_size: 8192
-
-### eval
-# eval_dataset: alpaca_en_demo
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/llama3_lora_eval.yaml

@@ -1,19 +0,0 @@
-### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-adapter_name_or_path: saves/llama3-8b/lora/sft
-trust_remote_code: true
-
-### method
-finetuning_type: lora
-
-### dataset
-task: mmlu_test  # choices: [mmlu_test, ceval_validation, cmmlu_test]
-template: fewshot
-lang: en
-n_shot: 5
-
-### output
-save_dir: saves/llama3-8b/lora/eval
-
-### eval
-batch_size: 4

examples/train_lora/llama3_lora_ppo.yaml

@@ -1,43 +0,0 @@
-### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-reward_model: saves/llama3-8b/lora/reward
-trust_remote_code: true
-
-### method
-stage: ppo
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: identity,alpaca_en_demo
-template: llama3
-cutoff_len: 2048
-max_samples: 1000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/llama3-8b/lora/ppo
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 8
-learning_rate: 1.0e-5
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-
-### generate
-max_new_tokens: 512
-top_k: 0
-top_p: 0.9

examples/train_lora/llama3_lora_sft.yaml

@@ -1,46 +0,0 @@
-### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: identity,alpaca_en_demo
-template: llama3
-cutoff_len: 2048
-max_samples: 1000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/llama3-8b/lora/sft
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-save_only_model: false
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 8
-learning_rate: 1.0e-4
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-resume_from_checkpoint: null
-
-### eval
-# eval_dataset: alpaca_en_demo
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/llama4_lora_sft_ds3.yaml

@@ -1,49 +0,0 @@
-# pip install git+https://github.com/hiyouga/transformers.git@llama4_train
-
-### model
-model_name_or_path: meta-llama/Llama-4-Scout-17B-16E-Instruct
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-deepspeed: examples/deepspeed/ds_z3_config.json  # choices: [ds_z0_config.json, ds_z2_config.json, ds_z3_config.json]
-
-### dataset
-dataset: mllm_demo,identity,alpaca_en_demo
-template: llama4
-cutoff_len: 2048
-max_samples: 1000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/llama4-8b/lora/sft
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-save_only_model: false
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 2
-learning_rate: 1.0e-4
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-resume_from_checkpoint: null
-
-### eval
-# eval_dataset: alpaca_en_demo
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/qwen3_lora_dpo.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -13,15 +13,14 @@ pref_loss: sigmoid  # choices: [sigmoid (dpo), orpo, simpo]
 
 ### dataset
 dataset: dpo_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/dpo
+output_dir: saves/qwen3-4b/lora/dpo
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_kto.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -12,15 +12,14 @@ pref_beta: 0.1
 
 ### dataset
 dataset: kto_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/kto
+output_dir: saves/qwen3-4b/lora/kto
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_pretrain.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -13,12 +13,11 @@ lora_target: all
 dataset: c4_demo
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/pretrain
+output_dir: saves/qwen3-4b/lora/pretrain
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_reward.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -11,15 +11,14 @@ lora_target: all
 
 ### dataset
 dataset: dpo_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/reward
+output_dir: saves/qwen3-4b/lora/reward
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_sft.sh

@@ -2,7 +2,7 @@
 
 set -x
 
-MODEL_PATH=meta-llama/Meta-Llama-3-8B-Instruct
+MODEL_PATH=Qwen/Qwen3-4B-Instruct-2507
 
 llamafactory-cli train \
     --model_name_or_path ${MODEL_PATH} \
@@ -13,13 +13,12 @@ llamafactory-cli train \
     --lora_rank 8 \
     --lora_target all \
     --dataset identity,alpaca_en_demo \
-    --template llama3 \
+    --template qwen3_nothink \
     --cutoff_len 2048 \
     --max_samples 1000 \
-    --overwrite_cache \
     --preprocessing_num_workers 16 \
     --dataloader_num_workers 4 \
-    --output_dir saves/llama3-8b/lora/sft \
+    --output_dir saves/qwen3-4b/lora/sft \
     --logging_steps 10 \
     --save_steps 500 \
     --plot_loss \

examples/train_lora/qwen3_lora_sft.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: openai/gpt-oss-20b
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -11,15 +11,14 @@ lora_target: all
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: gpt
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/gpt-20b/lora/sft
+output_dir: saves/qwen3-4b/lora/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_sft_ds3.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -12,15 +12,14 @@ deepspeed: examples/deepspeed/ds_z3_config.json  # choices: [ds_z0_config.json,
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/sft
+output_dir: saves/qwen3-4b/lora/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_sft_ray.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct  # or use local absolute path
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507  # or use local absolute path
 trust_remote_code: true
 
 ### method
@@ -12,10 +12,9 @@ lora_target: all
 ### dataset
 dataset: identity,alpaca_en_demo
 dataset_dir: REMOTE:llamafactory/demo_data  # or use local absolute path
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
@@ -29,7 +28,7 @@ save_only_model: false
 report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
 
 ### ray
-ray_run_name: llama3_8b_sft_lora
+ray_run_name: qwen3_4b_sft_lora
 ray_storage_path: ./saves
 ray_num_workers: 4  # Number of GPUs to use.
 placement_strategy: PACK

examples/train_lora/qwen3_preprocess.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -11,13 +11,12 @@ lora_target: all
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
-tokenized_path: saves/llama3-8b/dataset/sft
+tokenized_path: saves/qwen3-4b/dataset/sft
 
-### output
-output_dir: saves/llama3-8b/lora/sft
+### output (not used)
+output_dir: saves/qwen3-4b/lora/sft
 overwrite_output_dir: true

examples/train_lora/qwen3moe_lora_sft_kt.yaml

@@ -1,52 +0,0 @@
-### model
-model_name_or_path: Qwen/Qwen3-235B-A22B-Instruct-2507
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: identity, alpaca_en_demo
-template: qwen3_nothink
-cutoff_len: 2048
-max_samples: 100000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/Kllama_Qwen3MoE_235bA22b
-logging_steps: 10
-save_steps: 200
-plot_loss: true
-overwrite_output_dir: true
-save_only_model: false
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 8
-learning_rate: 1.0e-4
-num_train_epochs: 3
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-resume_from_checkpoint: null
-
-### ktransformers
-use_kt: true # use KTransformers as LoRA sft backend
-kt_optimize_rule: examples/kt_optimize_rules/Qwen3Moe-sft-amx.yaml
-cpu_infer: 32
-chunk_size: 8192
-
-### eval
-# eval_dataset: alpaca_en_demo
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/qwen3vl_lora_dpo.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true
@@ -15,15 +15,14 @@ pref_loss: sigmoid  # choices: [sigmoid (dpo), orpo, simpo]
 
 ### dataset
 dataset: rlhf_v
-template: qwen2_vl
+template: qwen3_vl_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/qwen2_5vl-7b/lora/dpo
+output_dir: saves/qwen3-vl-4b/lora/dpo
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3vl_lora_sft.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true
@@ -13,15 +13,14 @@ lora_target: all
 
 ### dataset
 dataset: mllm_demo,identity,alpaca_en_demo  # video: mllm_video_demo
-template: qwen2_vl
+template: qwen3_vl_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/qwen2_5vl-7b/lora/sft
+output_dir: saves/qwen3-vl-4b/lora/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true