mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-09-30 20:37:25 +00:00
peterjunparkandGitHub
b46a93705b
* archive previous version * update for 26.3 * update col width * add profiling sections * update .wordlist.txt
117 lines
4.2 KiB
YAML
117 lines
4.2 KiB
YAML
dockers:
|
|
- pull_tag: rocm/jax-training:maxtext-v26.3
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v26.3/images/sha256-548381e496fa1367772964341130cc014ee1a9a5ca715ff4ca3aa92960d162c3
|
|
components:
|
|
ROCm: 7.2.1
|
|
JAX: 0.8.2
|
|
Python: 3.12
|
|
Transformer Engine: 2.8.0.dev0+9b312832
|
|
hipBLASLt: 1.3.0+bfcf25fa18
|
|
model_groups:
|
|
- group: Meta Llama
|
|
tag: llama
|
|
models:
|
|
- model: Llama 2 7B
|
|
mad_tag: jax_maxtext_train_llama-2-7b
|
|
model_repo: Llama-2-7B
|
|
precision: bf16
|
|
primus_config_name: llama2_7B-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama2_7b.yml
|
|
gfx942: env_scripts/llama2_7b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- model: Llama 2 70B
|
|
mad_tag: jax_maxtext_train_llama-2-70b
|
|
model_repo: Llama-2-70B
|
|
precision: bf16
|
|
primus_config_name: llama2_70B-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama2_70b.yml
|
|
gfx942: env_scripts/llama2_70b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- model: Llama 3 8B
|
|
mad_tag: jax_maxtext_train_llama-3-8b
|
|
primus_config_name: llama3_8B-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama3_8b.yml
|
|
gfx942: env_scripts/llama3_8b.yml
|
|
doc_options: ["multi-node"]
|
|
- model: Llama 3 70B
|
|
mad_tag: jax_maxtext_train_llama-3-70b
|
|
primus_config_name: llama3_70B-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama3_70b.yml
|
|
gfx942: env_scripts/llama3_70b.yml
|
|
doc_options: ["multi-node"]
|
|
- model: Llama 3.1 8B
|
|
mad_tag: jax_maxtext_train_llama-3.1-8b
|
|
model_repo: Llama-3.1-8B
|
|
precision: bf16
|
|
doc_options: ["single-node"]
|
|
- model: Llama 3.1 70B
|
|
mad_tag: jax_maxtext_train_llama-3.1-70b
|
|
model_repo: Llama-3.1-70B
|
|
precision: bf16
|
|
doc_options: ["single-node"]
|
|
- model: Llama 3.1 405B (multi-node)
|
|
mad_tag: jax_maxtext_train_llama-3.1-405b
|
|
model_repo: Llama-3.1-405B
|
|
precision: bf16
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama3_405b.yml
|
|
doc_options: ["multi-node"]
|
|
- model: Llama 3.3 70B
|
|
mad_tag: jax_maxtext_train_llama-3.3-70b
|
|
model_repo: Llama-3.3-70B
|
|
precision: bf16
|
|
primus_config_name: llama3.3_70B-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama3.3_70b.yml
|
|
gfx942: env_scripts/llama3.3_70b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- group: DeepSeek
|
|
tag: deepseek
|
|
models:
|
|
- model: DeepSeek-V2-Lite (16B)
|
|
mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
|
|
model_repo: DeepSeek-V2-lite
|
|
precision: bf16
|
|
primus_config_name: deepseek_v2_16B-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_deepseek2_16b.yml
|
|
gfx942: env_scripts/deepseek2_16b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- group: Mistral AI
|
|
tag: mistral
|
|
models:
|
|
- model: Mixtral 8x7B
|
|
mad_tag: jax_maxtext_train_mixtral-8x7b
|
|
model_repo: Mixtral-8x7B
|
|
precision: bf16
|
|
primus_config_name: mixtral_8x7B-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_mixtral_8x7b.yml
|
|
gfx942: env_scripts/llama3_8x7b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- group: Qwen
|
|
tag: qwen
|
|
models:
|
|
- model: Qwen 14B
|
|
mad_tag: jax_maxtext_train_qwen3-14b
|
|
model_repo: Qwen3-14B
|
|
precision: bf16
|
|
primus_config_name: qwen3_14B-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_qwen3_14b.yml
|
|
gfx942: env_scripts/qwen3_14b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- model: Qwen 30B A3B
|
|
mad_tag: jax_maxtext_train_qwen3-30b-a3b
|
|
model_repo: Qwen3-30B-A3B
|
|
precision: bf16
|
|
primus_config_name: qwen3_30B_a3b-pretrain.yaml
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_qwen3_30b_a3b.yml
|
|
gfx942: env_scripts/qwen3_30b_a3b.yml
|
|
doc_options: ["single-node", "multi-node"]
|