mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-09-30 20:37:25 +00:00
peterjunparkandGitHub
4d156fcbb3
* add previous versions * Fix heading levels in pages using embedded templates (#5468) * update primus-megatron doc update megatron-lm doc update templates fix tab update primus-megatron model configs Update primus-pytorch model configs fix css class add posttrain to pytorch-training template update data sheets update update update update docker tags * Add known issue and update Primus/Turbo versions * add primus ver to histories * update primus ver to 0.1.1 * fix leftovers from merge conflict
179 lines
6.2 KiB
YAML
179 lines
6.2 KiB
YAML
dockers:
|
|
- pull_tag: rocm/pytorch-training:v25.8
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
|
|
components:
|
|
ROCm: 6.4.3
|
|
PyTorch: 2.8.0a0+gitd06a406
|
|
Python: 3.10.18
|
|
Transformer Engine: 2.2.0.dev0+a1e66aae
|
|
Flash Attention: 3.0.0.post1
|
|
hipBLASLt: 1.1.0-d1b517fc7a
|
|
model_groups:
|
|
- group: Meta Llama
|
|
tag: llama
|
|
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: [pretrain, finetune_fw, finetune_lora, HF_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, finetune_fw, finetune_lora]
|
|
- 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]
|
|
- 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]
|
|
- group: OpenAI
|
|
tag: openai
|
|
models:
|
|
- model: GPT OSS 20B
|
|
mad_tag: pyt_train_gpt_oss_20b
|
|
model_repo: GPT-OSS-20B
|
|
url: https://huggingface.co/openai/gpt-oss-20b
|
|
precision: BF16
|
|
training_modes: [HF_finetune_lora]
|
|
- model: GPT OSS 120B
|
|
mad_tag: pyt_train_gpt_oss_120b
|
|
model_repo: GPT-OSS-120B
|
|
url: https://huggingface.co/openai/gpt-oss-120b
|
|
precision: BF16
|
|
training_modes: [HF_finetune_lora]
|
|
- group: Qwen
|
|
tag: qwen
|
|
models:
|
|
- model: Qwen 3 8B
|
|
mad_tag: pyt_train_qwen3-8b
|
|
model_repo: Qwen3-8B
|
|
url: https://huggingface.co/Qwen/Qwen3-8B
|
|
precision: BF16
|
|
training_modes: [finetune_fw, finetune_lora]
|
|
- model: Qwen 3 32B
|
|
mad_tag: pyt_train_qwen3-32b
|
|
model_repo: Qwen3-32
|
|
url: https://huggingface.co/Qwen/Qwen3-32B
|
|
precision: BF16
|
|
training_modes: [finetune_lora]
|
|
- model: Qwen 2.5 32B
|
|
mad_tag: pyt_train_qwen2.5-32b
|
|
model_repo: Qwen2.5-32B
|
|
url: https://huggingface.co/Qwen/Qwen2.5-32B
|
|
precision: BF16
|
|
training_modes: [finetune_lora]
|
|
- model: Qwen 2.5 72B
|
|
mad_tag: pyt_train_qwen2.5-72b
|
|
model_repo: Qwen2.5-72B
|
|
url: https://huggingface.co/Qwen/Qwen2.5-72B
|
|
precision: BF16
|
|
training_modes: [finetune_lora]
|
|
- model: Qwen 2 1.5B
|
|
mad_tag: pyt_train_qwen2-1.5b
|
|
model_repo: Qwen2-1.5B
|
|
url: https://huggingface.co/Qwen/Qwen2-1.5B
|
|
precision: BF16
|
|
training_modes: [finetune_fw, finetune_lora]
|
|
- model: Qwen 2 7B
|
|
mad_tag: pyt_train_qwen2-7b
|
|
model_repo: Qwen2-7B
|
|
url: https://huggingface.co/Qwen/Qwen2-7B
|
|
precision: BF16
|
|
training_modes: [finetune_fw, finetune_lora]
|
|
- group: Stable Diffusion
|
|
tag: sd
|
|
models:
|
|
- model: Stable Diffusion XL
|
|
mad_tag: pyt_huggingface_stable_diffusion_xl_2k_lora_finetuning
|
|
model_repo: SDXL
|
|
url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
|
|
precision: BF16
|
|
training_modes: [finetune_lora]
|
|
- group: Flux
|
|
tag: flux
|
|
models:
|
|
- 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: NCF
|
|
tag: ncf
|
|
models:
|
|
- model: NCF
|
|
mad_tag: pyt_ncf_training
|
|
model_repo:
|
|
url: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Recommendation/NCF
|
|
precision: FP32
|