mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-11-02 19:03:06 +00:00
peterjunparkandGitHub
ed98e9e5cf
* Archive previous version - 26.2 * Update Megatron data and template ver hist page fix gpt fix * Update torch data and template hist page clean up * Remove legacy (non-Primus) from TOC add :no-search: * Update Primus commit hashes * Update multi-node examples update * fix anchors
76 lines
2.8 KiB
YAML
76 lines
2.8 KiB
YAML
docker:
|
|
pull_tag: rocm/primus:v26.2
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.2/images/sha256-9148d1bfcd579bf92f44bd89090e0d8c958f149c134b4b34b9674ab559244585
|
|
components:
|
|
ROCm: 7.2.0
|
|
PyTorch: 2.10.0a0+git449b176
|
|
Python: "3.12.3"
|
|
Transformer Engine: 2.8.0.dev0+51f74fa7
|
|
Flash Attention: 2.8.3
|
|
hipBLASLt: 1.2.0-de5c1aebb6
|
|
Triton: 3.6.0
|
|
RCCL: 2.27.7
|
|
model_groups:
|
|
- group: Meta Llama
|
|
tag: llama
|
|
models:
|
|
- model: Llama 3.3 70B
|
|
mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
|
|
config_name: llama3.3_70B-pretrain.yaml
|
|
- model: Llama 3.1 8B
|
|
mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
|
|
config_name: llama3.1_8B-pretrain.yaml
|
|
- model: Llama 3.1 70B
|
|
mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
|
|
config_name: llama3.1_70B-pretrain.yaml
|
|
- model: Llama 2 7B
|
|
mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
|
|
config_name: llama2_7B-pretrain.yaml
|
|
- model: Llama 2 70B
|
|
mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
|
|
config_name: llama2_70B-pretrain.yaml
|
|
- group: AMD Zebra-Llama
|
|
tag: zebra-llama
|
|
models:
|
|
- model: Zebra-Llama 1B
|
|
mad_tag: primus_pyt_megatron_lm_train_zebra-llama-1b
|
|
config_name: zebra_llama_1b-pretrain.yaml
|
|
- model: Zebra-Llama 3B
|
|
mad_tag: primus_pyt_megatron_lm_train_zebra-llama-3b
|
|
config_name: zebra_llama_3b-pretrain.yaml
|
|
- model: Zebra-Llama 8B
|
|
mad_tag: primus_pyt_megatron_lm_train_zebra-llama-8b
|
|
config_name: zebra_llama_8b-pretrain.yaml
|
|
- group: DeepSeek
|
|
tag: deepseek
|
|
models:
|
|
- model: DeepSeek-V3 (proxy)
|
|
mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
|
|
config_name: deepseek_v3-pretrain.yaml
|
|
- model: DeepSeek-V2-Lite
|
|
mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
|
|
config_name: deepseek_v2_lite-pretrain.yaml
|
|
- group: Mistral AI
|
|
tag: mistral
|
|
models:
|
|
- model: Mixtral 8x7B
|
|
mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
|
|
config_name: mixtral_8x7B_v0.1-pretrain.yaml
|
|
- model: Mixtral 8x22B (proxy)
|
|
mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
|
|
config_name: mixtral_8x22B_v0.1-pretrain.yaml
|
|
- group: Qwen
|
|
tag: qwen
|
|
models:
|
|
- model: Qwen 3 32B SFT
|
|
mad_tag: primus_pyt_megatron_lm_train_qwen3-32b-sft
|
|
- model: Qwen 3 32B LoRA
|
|
mad_tag: primus_pyt_megatron_lm_train_qwen3-32b-lora
|
|
config_name: primus_qwen2.5_7B-pretrain.yaml
|
|
- model: Qwen 2.5 7B
|
|
mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
|
|
config_name: primus_qwen2.5_7B-pretrain.yaml
|
|
- model: Qwen 2.5 72B
|
|
mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
|
|
config_name: qwen2.5_72B-pretrain.yaml
|