ROCm/docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.6-benchmark-models.yaml

unified_docker:
  latest:
    pull_tag: rocm/pytorch-training:v25.6
    docker_hub_url: https://hub.docker.com/r/rocm/pytorch-training/tags
    rocm_version: 6.4.1
    pytorch_version: 2.8.0a0+git7d205b2
    python_version: 3.10.17
    transformer_engine_version: 1.14.0+2f85f5f2
    flash_attention_version: 3.0.0.post1
    hipblaslt_version: 0.15.0-8c6919d
    triton_version: 3.3.0
model_groups:
  - group: Pre-training
    tag: pre-training
    models:
    - model: Llama 3.1 8B
      mad_tag: pyt_train_llama-3.1-8b
      model_repo: Llama-3.1-8B
      url: https://huggingface.co/meta-llama/Llama-3.1-8B
      precision: BF16
      training_modes: [pretrain]
    - model: Llama 3.1 70B
      mad_tag: pyt_train_llama-3.1-70b
      model_repo: Llama-3.1-70B
      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
      precision: BF16
      training_modes: [pretrain]
    - model: FLUX.1-dev
      mad_tag: pyt_train_flux
      model_repo: Flux
      url: https://huggingface.co/black-forest-labs/FLUX.1-dev
      precision: BF16
      training_modes: [pretrain]
  - group: Fine-tuning
    tag: fine-tuning
    models:
    - model: Llama 4 Scout 17B-16E
      mad_tag: pyt_train_llama-4-scout-17b-16e
      model_repo: Llama-4-17B_16E
      url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E
      precision: BF16
      training_modes: [finetune_fw, finetune_lora]
    - model: Llama 3.3 70B
      mad_tag: pyt_train_llama-3.3-70b
      model_repo: Llama-3.3-70B
      url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
      precision: BF16
      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
    - model: Llama 3.2 1B
      mad_tag: pyt_train_llama-3.2-1b
      model_repo: Llama-3.2-1B
      url: https://huggingface.co/meta-llama/Llama-3.2-1B
      precision: BF16
      training_modes: [finetune_fw, finetune_lora]
    - model: Llama 3.2 3B
      mad_tag: pyt_train_llama-3.2-3b
      model_repo: Llama-3.2-3B
      url: https://huggingface.co/meta-llama/Llama-3.2-3B
      precision: BF16
      training_modes: [finetune_fw, finetune_lora]
    - model: Llama 3.2 Vision 11B
      mad_tag: pyt_train_llama-3.2-vision-11b
      model_repo: Llama-3.2-Vision-11B
      url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision
      precision: BF16
      training_modes: [finetune_fw]
    - model: Llama 3.2 Vision 90B
      mad_tag: pyt_train_llama-3.2-vision-90b
      model_repo: Llama-3.2-Vision-90B
      url: https://huggingface.co/meta-llama/Llama-3.2-90B-Vision
      precision: BF16
      training_modes: [finetune_fw]
    - model: Llama 3.1 8B
      mad_tag: pyt_train_llama-3.1-8b
      model_repo: Llama-3.1-8B
      url: https://huggingface.co/meta-llama/Llama-3.1-8B
      precision: BF16
      training_modes: [finetune_fw, finetune_lora]
    - model: Llama 3.1 70B
      mad_tag: pyt_train_llama-3.1-70b
      model_repo: Llama-3.1-70B
      url: https://huggingface.co/meta-llama/Llama-3.1-70B
      precision: BF16
      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
    - model: Llama 3.1 405B
      mad_tag: pyt_train_llama-3.1-405b
      model_repo: Llama-3.1-405B
      url: https://huggingface.co/meta-llama/Llama-3.1-405B
      precision: BF16
      training_modes: [finetune_qlora, HF_finetune_lora]
    - model: Llama 3 8B
      mad_tag: pyt_train_llama-3-8b
      model_repo: Llama-3-8B
      url: https://huggingface.co/meta-llama/Meta-Llama-3-8B
      precision: BF16
      training_modes: [finetune_fw, finetune_lora]
    - model: Llama 3 70B
      mad_tag: pyt_train_llama-3-70b
      model_repo: Llama-3-70B
      url: https://huggingface.co/meta-llama/Meta-Llama-3-70B
      precision: BF16
      training_modes: [finetune_fw, finetune_lora]
    - model: Llama 2 7B
      mad_tag: pyt_train_llama-2-7b
      model_repo: Llama-2-7B
      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
      precision: BF16
      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
    - model: Llama 2 13B
      mad_tag: pyt_train_llama-2-13b
      model_repo: Llama-2-13B
      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
      precision: BF16
      training_modes: [finetune_fw, finetune_lora]
    - model: Llama 2 70B
      mad_tag: pyt_train_llama-2-70b
      model_repo: Llama-2-70B
      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
      precision: BF16
      training_modes: [finetune_lora, finetune_qlora, HF_finetune_lora]